Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:554ac76717b212531d487f826d6f56be0885baa17fbb23deb0b021b0b65b2f13
+oid sha256:4a76e3b7376f20d6fcdd5aabb63c0ab16c043b32e2b7dbf9950ba36d3020f24b
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d32415e80e85feda35ed2a908559f19ac29ad6a54e828bab7c25f6a83b3ea21e
+oid sha256:2c33babc82d5c51590dec3f18ac7d982254164ed69bb16834f9adefb17093787
 size 407121750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0714cccf9e05fe593f5ea870602d0318c86b16af3be10896beafa4c7a48d7aa5
+oid sha256:1e39d0af2cf4b87774b10590120a870543f9b08e53cedf7ba105ba8ca2c73da7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007001526332740537,
+  "epoch": 0.0014003052665481075,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 3.001,
       "eval_steps_per_second": 1.5,
       "step": 25
+    },
+    {
+      "epoch": 0.0007281587386050159,
+      "grad_norm": 1.333717942237854,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.1736,
+      "step": 26
+    },
+    {
+      "epoch": 0.000756164843935978,
+      "grad_norm": 1.4034525156021118,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 1.2473,
+      "step": 27
+    },
+    {
+      "epoch": 0.0007841709492669402,
+      "grad_norm": 1.6855180263519287,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 1.5994,
+      "step": 28
+    },
+    {
+      "epoch": 0.0008121770545979023,
+      "grad_norm": 1.4234453439712524,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 1.1151,
+      "step": 29
+    },
+    {
+      "epoch": 0.0008401831599288645,
+      "grad_norm": 1.4440644979476929,
+      "learning_rate": 5e-05,
+      "loss": 1.389,
+      "step": 30
+    },
+    {
+      "epoch": 0.0008401831599288645,
+      "eval_loss": 1.3428627252578735,
+      "eval_runtime": 5009.2202,
+      "eval_samples_per_second": 3.001,
+      "eval_steps_per_second": 1.501,
+      "step": 30
+    },
+    {
+      "epoch": 0.0008681892652598267,
+      "grad_norm": 1.7354429960250854,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 1.1572,
+      "step": 31
+    },
+    {
+      "epoch": 0.0008961953705907888,
+      "grad_norm": 3.8051087856292725,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.4318,
+      "step": 32
+    },
+    {
+      "epoch": 0.0009242014759217509,
+      "grad_norm": 1.5283364057540894,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 1.3123,
+      "step": 33
+    },
+    {
+      "epoch": 0.0009522075812527131,
+      "grad_norm": 1.352604866027832,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3531,
+      "step": 34
+    },
+    {
+      "epoch": 0.0009802136865836753,
+      "grad_norm": 1.7521588802337646,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3434,
+      "step": 35
+    },
+    {
+      "epoch": 0.0009802136865836753,
+      "eval_loss": 1.3325791358947754,
+      "eval_runtime": 5008.929,
+      "eval_samples_per_second": 3.002,
+      "eval_steps_per_second": 1.501,
+      "step": 35
+    },
+    {
+      "epoch": 0.0010082197919146375,
+      "grad_norm": 1.2757823467254639,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.3256,
+      "step": 36
+    },
+    {
+      "epoch": 0.0010362258972455996,
+      "grad_norm": 1.1284574270248413,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 1.2034,
+      "step": 37
+    },
+    {
+      "epoch": 0.0010642320025765616,
+      "grad_norm": 1.2620298862457275,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.6568,
+      "step": 38
+    },
+    {
+      "epoch": 0.0010922381079075238,
+      "grad_norm": 1.244226336479187,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.2673,
+      "step": 39
+    },
+    {
+      "epoch": 0.001120244213238486,
+      "grad_norm": 1.1295228004455566,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4755,
+      "step": 40
+    },
+    {
+      "epoch": 0.001120244213238486,
+      "eval_loss": 1.3263696432113647,
+      "eval_runtime": 5009.0341,
+      "eval_samples_per_second": 3.002,
+      "eval_steps_per_second": 1.501,
+      "step": 40
+    },
+    {
+      "epoch": 0.0011482503185694481,
+      "grad_norm": 1.3037229776382446,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.4539,
+      "step": 41
+    },
+    {
+      "epoch": 0.0011762564239004103,
+      "grad_norm": 1.3781661987304688,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0606,
+      "step": 42
+    },
+    {
+      "epoch": 0.0012042625292313725,
+      "grad_norm": 1.5477420091629028,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.6065,
+      "step": 43
+    },
+    {
+      "epoch": 0.0012322686345623347,
+      "grad_norm": 1.5209083557128906,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.4001,
+      "step": 44
+    },
+    {
+      "epoch": 0.0012602747398932968,
+      "grad_norm": 1.1803650856018066,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.399,
+      "step": 45
+    },
+    {
+      "epoch": 0.0012602747398932968,
+      "eval_loss": 1.3230071067810059,
+      "eval_runtime": 5009.7608,
+      "eval_samples_per_second": 3.001,
+      "eval_steps_per_second": 1.501,
+      "step": 45
+    },
+    {
+      "epoch": 0.0012882808452242588,
+      "grad_norm": 1.2966963052749634,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.2219,
+      "step": 46
+    },
+    {
+      "epoch": 0.001316286950555221,
+      "grad_norm": 1.1639353036880493,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.9402,
+      "step": 47
+    },
+    {
+      "epoch": 0.0013442930558861831,
+      "grad_norm": 1.3903875350952148,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.2695,
+      "step": 48
+    },
+    {
+      "epoch": 0.0013722991612171453,
+      "grad_norm": 1.8993217945098877,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 1.5358,
+      "step": 49
+    },
+    {
+      "epoch": 0.0014003052665481075,
+      "grad_norm": 0.992319643497467,
+      "learning_rate": 0.0,
+      "loss": 0.9032,
+      "step": 50
+    },
+    {
+      "epoch": 0.0014003052665481075,
+      "eval_loss": 1.3224403858184814,
+      "eval_runtime": 5007.1747,
+      "eval_samples_per_second": 3.003,
+      "eval_steps_per_second": 1.501,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8294216761344000.0,
+  "total_flos": 1.6588433522688e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null