Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9d151b104e4587302b381f9c77157376ae6196f5cd84d137a15f82b1a18dfc7
+oid sha256:54c7cf4a7134d9f5f81ac1db1b48c3dc0d167316859f88ea5018594199325a15
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11eb741cbdea64555ffe51eef07ccaf042fa2e0131bffcf5fceda8d5cf1cf23c
+oid sha256:a5acf7e19e5d6d050cabae47ac6ec48bde77d0137e8523c5169c289f0894e857
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
+oid sha256:70bb08e79cd87e26411515d4cfe540a1dfafd998745c321dfb4680b9ed334a58
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021087407303272063,
+  "epoch": 0.028116543071029416,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 361.694,
       "eval_steps_per_second": 180.907,
       "step": 150
+    },
+    {
+      "epoch": 0.022493234456823535,
+      "grad_norm": 0.08426641672849655,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 10.3172,
+      "step": 160
+    },
+    {
+      "epoch": 0.023899061610375003,
+      "grad_norm": 0.08034799993038177,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 10.3158,
+      "step": 170
+    },
+    {
+      "epoch": 0.025304888763926475,
+      "grad_norm": 0.08645985275506973,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 10.3162,
+      "step": 180
+    },
+    {
+      "epoch": 0.026710715917477947,
+      "grad_norm": 0.07937773317098618,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 10.318,
+      "step": 190
+    },
+    {
+      "epoch": 0.028116543071029416,
+      "grad_norm": 0.08613844960927963,
+      "learning_rate": 0.0,
+      "loss": 10.3155,
+      "step": 200
+    },
+    {
+      "epoch": 0.028116543071029416,
+      "eval_loss": 10.315034866333008,
+      "eval_runtime": 8.2442,
+      "eval_samples_per_second": 363.284,
+      "eval_steps_per_second": 181.703,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1942868951040.0,
+  "total_flos": 2589414359040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null