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:e0d54388443ec393e4174e0ff722e73d9f16bbc15628918fc5a5f7379ad1b1c3
+oid sha256:becc9e2576c48d7ed21204d5774075e23b76024b6d02784ec9a926c379db999d
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cadda56dab8914de7a54dbe8684ee28f2fc8c54b0c8305541b34eafef991e48
+oid sha256:c1f07028f18039744581420bb7020cd14b00d41cb64c178a88b3c68a98ed3860
 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:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011504170261719874,
+  "epoch": 0.015338893682293164,
   "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": 336.852,
       "eval_steps_per_second": 168.426,
       "step": 150
+    },
+    {
+      "epoch": 0.012271114945834532,
+      "grad_norm": 0.1478935182094574,
+      "learning_rate": 0.0002,
+      "loss": 10.319,
+      "step": 160
+    },
+    {
+      "epoch": 0.01303805962994919,
+      "grad_norm": 0.14732635021209717,
+      "learning_rate": 0.0002,
+      "loss": 10.3149,
+      "step": 170
+    },
+    {
+      "epoch": 0.013805004314063849,
+      "grad_norm": 0.12901423871517181,
+      "learning_rate": 0.0002,
+      "loss": 10.314,
+      "step": 180
+    },
+    {
+      "epoch": 0.014571948998178506,
+      "grad_norm": 0.1489384025335312,
+      "learning_rate": 0.0002,
+      "loss": 10.3089,
+      "step": 190
+    },
+    {
+      "epoch": 0.015338893682293164,
+      "grad_norm": 0.1256222128868103,
+      "learning_rate": 0.0002,
+      "loss": 10.3102,
+      "step": 200
+    },
+    {
+      "epoch": 0.015338893682293164,
+      "eval_loss": 10.30687141418457,
+      "eval_runtime": 16.2741,
+      "eval_samples_per_second": 337.346,
+      "eval_steps_per_second": 168.673,
+      "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": 3685308825600.0,
+  "total_flos": 4933141463040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null