Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:400fa371e0623cd4e37a6918de4c2e656bd4fc4801b38819eaf9108f928863ff
+oid sha256:5cc3877187620d217bec3d32516bbfed44b14328f78a65084e3ce12ff22cdc68
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf7f6775fc8c4d5a4980d27667fa3ce41e99804c75cfe1aeefb377747b7e16d
+oid sha256:1ce1d872f7298a1cd26c66b734cb1af38e5270d4e6e7d9b4fad602c22db8fb04
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b61b261b7271f58efb286e9fdbe766600d08768b764e4ddc8ae15e5645ce955a
+oid sha256:bdb9fc32e018ea5e31c4bdff50abbb644dc74074b27dbfcce5626f04b48d04d0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005182152666217547,
+  "epoch": 0.0077732289993263206,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 5.269,
       "eval_steps_per_second": 2.635,
       "step": 50
+    },
+    {
+      "epoch": 0.005285795719541898,
+      "grad_norm": 3.99528431892395,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1937,
+      "step": 51
+    },
+    {
+      "epoch": 0.005389438772866248,
+      "grad_norm": 2.4772651195526123,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.9038,
+      "step": 52
+    },
+    {
+      "epoch": 0.0054930818261906,
+      "grad_norm": 2.4386355876922607,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.7842,
+      "step": 53
+    },
+    {
+      "epoch": 0.00559672487951495,
+      "grad_norm": 2.42254638671875,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7758,
+      "step": 54
+    },
+    {
+      "epoch": 0.005700367932839301,
+      "grad_norm": 2.059051513671875,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.5559,
+      "step": 55
+    },
+    {
+      "epoch": 0.0058040109861636525,
+      "grad_norm": 2.1774046421051025,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.6853,
+      "step": 56
+    },
+    {
+      "epoch": 0.005907654039488003,
+      "grad_norm": 1.9030838012695312,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7179,
+      "step": 57
+    },
+    {
+      "epoch": 0.006011297092812355,
+      "grad_norm": 1.7430174350738525,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.5938,
+      "step": 58
+    },
+    {
+      "epoch": 0.006114940146136705,
+      "grad_norm": 1.5580425262451172,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.4777,
+      "step": 59
+    },
+    {
+      "epoch": 0.006218583199461056,
+      "grad_norm": 1.6430137157440186,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6449,
+      "step": 60
+    },
+    {
+      "epoch": 0.006322226252785407,
+      "grad_norm": 1.7808021306991577,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.61,
+      "step": 61
+    },
+    {
+      "epoch": 0.006425869306109758,
+      "grad_norm": 1.6967010498046875,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.6651,
+      "step": 62
+    },
+    {
+      "epoch": 0.006529512359434109,
+      "grad_norm": 2.296234607696533,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7242,
+      "step": 63
+    },
+    {
+      "epoch": 0.00663315541275846,
+      "grad_norm": 1.8341970443725586,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.7411,
+      "step": 64
+    },
+    {
+      "epoch": 0.006736798466082811,
+      "grad_norm": 1.8200284242630005,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.7295,
+      "step": 65
+    },
+    {
+      "epoch": 0.0068404415194071614,
+      "grad_norm": 2.3568577766418457,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7988,
+      "step": 66
+    },
+    {
+      "epoch": 0.006944084572731513,
+      "grad_norm": 1.7270454168319702,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.6691,
+      "step": 67
+    },
+    {
+      "epoch": 0.0070477276260558636,
+      "grad_norm": 2.04880428314209,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.6808,
+      "step": 68
+    },
+    {
+      "epoch": 0.007151370679380214,
+      "grad_norm": 1.5405012369155884,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6412,
+      "step": 69
+    },
+    {
+      "epoch": 0.007255013732704566,
+      "grad_norm": 2.134209394454956,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.8178,
+      "step": 70
+    },
+    {
+      "epoch": 0.007358656786028916,
+      "grad_norm": 1.8445318937301636,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.6008,
+      "step": 71
+    },
+    {
+      "epoch": 0.007462299839353267,
+      "grad_norm": 2.9138455390930176,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.805,
+      "step": 72
+    },
+    {
+      "epoch": 0.0075659428926776184,
+      "grad_norm": 1.6262131929397583,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.7325,
+      "step": 73
+    },
+    {
+      "epoch": 0.007669585946001969,
+      "grad_norm": 3.171100378036499,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.8451,
+      "step": 74
+    },
+    {
+      "epoch": 0.0077732289993263206,
+      "grad_norm": 2.2660341262817383,
+      "learning_rate": 0.0,
+      "loss": 0.7428,
+      "step": 75
+    },
+    {
+      "epoch": 0.0077732289993263206,
+      "eval_loss": 0.0836588591337204,
+      "eval_runtime": 1542.323,
+      "eval_samples_per_second": 5.269,
+      "eval_steps_per_second": 2.634,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.44383432317993e+16,
+  "total_flos": 1.1439811893343027e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null