Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5446bcf23e040304bc59b749a93897127aee277208fdf1fbb75359c6fa511903
+oid sha256:00c46697e5c717cbeff2e837e99bdd67f3556e46f8bcb69c389cb508b84fb68a
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20112ad026ee17a6f3cfc18626eec5d460d422e5642ab12d1d5c76b86180cf3b
+oid sha256:6599550d42336a35de409b692cbf681921b4e5360a47ef3ad2dbd062f464e790
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8993bf6628306cfa4308a498856a6f9448ca981b1ea716342545995bef76afd9
+oid sha256:a0c7f32efece8b86d108778cc2db4c228f1cfc0fc3e11c6de3c5c5623699f970
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.437636761487965,
+  "epoch": 0.6564551422319475,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 24.576,
       "eval_steps_per_second": 12.415,
       "step": 100
+    },
+    {
+      "epoch": 0.4814004376367615,
+      "grad_norm": 1.2032049894332886,
+      "learning_rate": 0.0002,
+      "loss": 0.2868,
+      "step": 110
+    },
+    {
+      "epoch": 0.5251641137855579,
+      "grad_norm": 0.9359709024429321,
+      "learning_rate": 0.0002,
+      "loss": 0.308,
+      "step": 120
+    },
+    {
+      "epoch": 0.5689277899343544,
+      "grad_norm": 1.3596349954605103,
+      "learning_rate": 0.0002,
+      "loss": 0.352,
+      "step": 130
+    },
+    {
+      "epoch": 0.612691466083151,
+      "grad_norm": 0.8330109715461731,
+      "learning_rate": 0.0002,
+      "loss": 0.2522,
+      "step": 140
+    },
+    {
+      "epoch": 0.6564551422319475,
+      "grad_norm": 1.0199737548828125,
+      "learning_rate": 0.0002,
+      "loss": 0.2819,
+      "step": 150
+    },
+    {
+      "epoch": 0.6564551422319475,
+      "eval_loss": 0.2861652076244354,
+      "eval_runtime": 3.9483,
+      "eval_samples_per_second": 24.567,
+      "eval_steps_per_second": 12.41,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.122743621353472e+16,
+  "total_flos": 3.184115432030208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null