Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6088f7c359796cb7ff30adc74aa0f8d294d64262cec14e7b1a6fbea974039c8e
+oid sha256:55ed7a3ecb10bf42843b4c915767eaa851e7d02859f00ffe0d9f7fe0085b0dc1
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffdc12bbc6f111764f515d66d3abf29cbc5b2ec09f92aae64a7343026dabce21
+oid sha256:39b6b4a09d60892d9bc378bf3f6fbe4403d87c71bb5ad8e3b7a0b295cb5ca09f
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfd197233abf432c0c23452d37e2c9eac62609b8e7d27929b13fe5bd30a4bf41
+oid sha256:e2016bcdd9ab3768f545f9d12095da67be199dcc219634b31be42ed5524ee23f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.008603216071348e-05,
+  "epoch": 0.00018017206432142696,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 13.43,
       "eval_steps_per_second": 6.715,
       "step": 3
+    },
+    {
+      "epoch": 0.00012011470954761798,
+      "grad_norm": 0.283048540353775,
+      "learning_rate": 8e-05,
+      "loss": 0.3772,
+      "step": 4
+    },
+    {
+      "epoch": 0.00015014338693452247,
+      "grad_norm": 0.6533939838409424,
+      "learning_rate": 0.0001,
+      "loss": 0.3009,
+      "step": 5
+    },
+    {
+      "epoch": 0.00018017206432142696,
+      "grad_norm": 0.32610440254211426,
+      "learning_rate": 0.00012,
+      "loss": 0.4086,
+      "step": 6
+    },
+    {
+      "epoch": 0.00018017206432142696,
+      "eval_loss": 0.3601542115211487,
+      "eval_runtime": 1044.8592,
+      "eval_samples_per_second": 13.42,
+      "eval_steps_per_second": 6.71,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1662257190666240.0,
+  "total_flos": 3324514381332480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null