Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf2922a4363f5fa6cf8d574029e9d6ba31ac1d3b7629674d4031a4f44cf3920
+oid sha256:26f43d2c3743bd9f4895a6cddbad335f65c73b7b9d2824ff8b86c77ae2368c6f
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c909dd663a1e9c080c8f0ef5509f27230eda1b58f1ea3f02abb033c763db7767
+oid sha256:da9cd5b15d668c1d91846196d90072e46488fdc03d7c0eeb04cfc707fa23a0a5
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0041939711664482305,
+  "epoch": 0.008387942332896461,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 692.411,
       "eval_steps_per_second": 346.206,
       "step": 2
+    },
+    {
+      "epoch": 0.006290956749672346,
+      "grad_norm": 0.01226983405649662,
+      "learning_rate": 3e-05,
+      "loss": 11.9304,
+      "step": 3
+    },
+    {
+      "epoch": 0.008387942332896461,
+      "grad_norm": 0.010739377699792385,
+      "learning_rate": 4e-05,
+      "loss": 11.9305,
+      "step": 4
+    },
+    {
+      "epoch": 0.008387942332896461,
+      "eval_loss": 11.931066513061523,
+      "eval_runtime": 1.1762,
+      "eval_samples_per_second": 683.538,
+      "eval_steps_per_second": 341.769,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 945291264.0,
+  "total_flos": 1890582528.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null