Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d87ebbefa1ec74136ed9645215ce1a2a7d6ecffe441e9992629216fb253770
+oid sha256:5173e389550d19c97205e17a23d26e7888e4bad5e689dd69ce407234f27f736c
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2920321d6e912527e51bdd8fc36661f58b3ff3804d8d9047415645854827097
+oid sha256:0dbf36b359843c55900366e858f78350c6bbc4047522062ea0a98c6ac759a813
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdf90a5cd51135a1af976686360cc954573fd5c044962ccc8a92b475436759ba
+oid sha256:bffe7c2454336adf1073b700dbbf9ab38b312b4e28fdb7704aa022403a69ca2d
 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": 0.0006279106273873685,
+  "epoch": 0.001255821254774737,
   "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": 26.888,
       "eval_steps_per_second": 13.444,
       "step": 3
+    },
+    {
+      "epoch": 0.0008372141698498247,
+      "grad_norm": 1.9130076169967651,
+      "learning_rate": 8e-05,
+      "loss": 2.6446,
+      "step": 4
+    },
+    {
+      "epoch": 0.0010465177123122808,
+      "grad_norm": 1.8720148801803589,
+      "learning_rate": 0.0001,
+      "loss": 2.659,
+      "step": 5
+    },
+    {
+      "epoch": 0.001255821254774737,
+      "grad_norm": 1.7725203037261963,
+      "learning_rate": 0.00012,
+      "loss": 2.4155,
+      "step": 6
+    },
+    {
+      "epoch": 0.001255821254774737,
+      "eval_loss": 2.3963053226470947,
+      "eval_runtime": 74.9235,
+      "eval_samples_per_second": 26.854,
+      "eval_steps_per_second": 13.427,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 262551098621952.0,
+  "total_flos": 550107063779328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null