Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d4ef48f4855b10201b3a6a26cd87a8cba96229d883aa937285be149bcc07ce
+oid sha256:71d5746b14bd34a16332bcbefcf3fa08eff902e1b13c30d4399bf12c452a4d64
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b922dfca56071d60da2def7af602f0cc536eac480193ea90bb51de53851e37c
+oid sha256:42a1b93d4398dea3c9802f7e59ed557ae03c0c238ebd7eb30c75bbd8c62fd7a6
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64c6abf8e0b4b068c9ccf580fad8106c176f0bcbeb6a5281c47aae019137f21
+oid sha256:4fc49fc65751e58a3cb574747cbcb5e4c948a9f894781b45993a63dc20612d30
 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": 0.2451982018798529,
+  "epoch": 0.3269309358398038,
   "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": 23.518,
       "eval_steps_per_second": 11.759,
       "step": 150
+    },
+    {
+      "epoch": 0.2615447486718431,
+      "grad_norm": 1.81687331199646,
+      "learning_rate": 0.0002,
+      "loss": 1.2538,
+      "step": 160
+    },
+    {
+      "epoch": 0.2778912954638333,
+      "grad_norm": 1.7752971649169922,
+      "learning_rate": 0.0002,
+      "loss": 1.0968,
+      "step": 170
+    },
+    {
+      "epoch": 0.29423784225582345,
+      "grad_norm": 1.5799192190170288,
+      "learning_rate": 0.0002,
+      "loss": 1.1737,
+      "step": 180
+    },
+    {
+      "epoch": 0.31058438904781366,
+      "grad_norm": 1.6626818180084229,
+      "learning_rate": 0.0002,
+      "loss": 1.2231,
+      "step": 190
+    },
+    {
+      "epoch": 0.3269309358398038,
+      "grad_norm": 1.9949339628219604,
+      "learning_rate": 0.0002,
+      "loss": 1.249,
+      "step": 200
+    },
+    {
+      "epoch": 0.3269309358398038,
+      "eval_loss": 1.239590048789978,
+      "eval_runtime": 10.9647,
+      "eval_samples_per_second": 23.53,
+      "eval_steps_per_second": 11.765,
+      "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": 3.543186492358656e+16,
+  "total_flos": 4.72600880873472e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null