Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:419ef2c365b2df61990765df67db820969667778e123c6c39e29b83cc59610e1
+oid sha256:53555ee8a4eb110c4bdce3fd50ed70e1c37d2228502979597728308e7dbc4c8a
 size 1912664024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceafd3de144036993fa29e2a17c0194470e240a1f774ed6130da298efb1038af
+oid sha256:1645b3ce8c7b797e757add674024ac2f3c2bdadc80e8a598a873bcc34e1ba413
 size 958697364

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:399c6e0a1a129bcf47d55d6652cc4710de81e426cb3bb5b9430151acfb862766
+oid sha256:caf99753320d5a922d21785c9acff8aad90fb47892dad1f221c94717bf3a04b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:857bbe62f2d165935d1ce9ae82dd80a72b9db823aa28c4ae95a8b905e80accaa
+oid sha256:21226719b9e25fe4304ec632d533e056eb568a7272feb0ef7163c162da3912fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009203018590097553,
+  "epoch": 0.012270691453463402,
   "eval_steps": 20,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,51 @@
       "eval_samples_per_second": 3.815,
       "eval_steps_per_second": 0.496,
       "step": 140
+    },
+    {
+      "epoch": 0.009816553162770723,
+      "grad_norm": 0.09732338786125183,
+      "learning_rate": 0.00019936594943958114,
+      "loss": 1.7397,
+      "step": 160
+    },
+    {
+      "epoch": 0.009816553162770723,
+      "eval_loss": 1.7010047435760498,
+      "eval_runtime": 25.8266,
+      "eval_samples_per_second": 3.872,
+      "eval_steps_per_second": 0.503,
+      "step": 160
+    },
+    {
+      "epoch": 0.011043622308117063,
+      "grad_norm": 0.11193066835403442,
+      "learning_rate": 0.0001992841364640432,
+      "loss": 1.7868,
+      "step": 180
+    },
+    {
+      "epoch": 0.011043622308117063,
+      "eval_loss": 1.6764620542526245,
+      "eval_runtime": 26.1757,
+      "eval_samples_per_second": 3.82,
+      "eval_steps_per_second": 0.497,
+      "step": 180
+    },
+    {
+      "epoch": 0.012270691453463402,
+      "grad_norm": 0.10227545350790024,
+      "learning_rate": 0.0001992023234885053,
+      "loss": 1.7799,
+      "step": 200
+    },
+    {
+      "epoch": 0.012270691453463402,
+      "eval_loss": 1.656005859375,
+      "eval_runtime": 26.2305,
+      "eval_samples_per_second": 3.812,
+      "eval_steps_per_second": 0.496,
+      "step": 200
     }
   ],
   "logging_steps": 20,
@@ -119,7 +164,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
-  "total_flos": 1.02462852169728e+16,
+  "total_flos": 1.41326994253824e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null