Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e23a239d6297d3c02bb38cbb0f1271275b709dcbdeb8dd00039dace5557b950
+oid sha256:c09ea6ce50093c41f2f5fb8b4e6414b0c577151e86f47fe18188690e6492eb39
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f23fb542af297c715b6dd28412917ef1b6b037abfdd12e08871b61d04ea5ea3
+oid sha256:39ca64088c14fde06f9661cede8c9942fee2ff16eb48934cb42c77609210f140
 size 60386772

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": 5.081,
       "eval_steps_per_second": 0.66,
       "step": 140
+    },
+    {
+      "epoch": 0.009816553162770723,
+      "grad_norm": 0.623275637626648,
+      "learning_rate": 0.00019936594943958114,
+      "loss": 1.6708,
+      "step": 160
+    },
+    {
+      "epoch": 0.009816553162770723,
+      "eval_loss": 1.629647970199585,
+      "eval_runtime": 19.5744,
+      "eval_samples_per_second": 5.109,
+      "eval_steps_per_second": 0.664,
+      "step": 160
+    },
+    {
+      "epoch": 0.011043622308117063,
+      "grad_norm": 0.6912758350372314,
+      "learning_rate": 0.0001992841364640432,
+      "loss": 1.7161,
+      "step": 180
+    },
+    {
+      "epoch": 0.011043622308117063,
+      "eval_loss": 1.6033389568328857,
+      "eval_runtime": 19.6839,
+      "eval_samples_per_second": 5.08,
+      "eval_steps_per_second": 0.66,
+      "step": 180
+    },
+    {
+      "epoch": 0.012270691453463402,
+      "grad_norm": 0.6177836656570435,
+      "learning_rate": 0.0001992023234885053,
+      "loss": 1.7165,
+      "step": 200
+    },
+    {
+      "epoch": 0.012270691453463402,
+      "eval_loss": 1.5879381895065308,
+      "eval_runtime": 19.7091,
+      "eval_samples_per_second": 5.074,
+      "eval_steps_per_second": 0.66,
+      "step": 200
     }
   ],
   "logging_steps": 20,
@@ -119,7 +164,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
-  "total_flos": 9140460390236160.0,
+  "total_flos": 1.25490630177792e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null