Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ba094ad598aa95aed793b98e633eadfb86c62b48584ff1c483f91e725531d2b
+oid sha256:f269de2521f0d1e002ee3d77fa3b033214ec5f9b431159cdf52b7fdea1f0cf3d
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71f907b8c59d869733baaeafd9d203d6e40b2bebb4873d145e497d995a6982d8
+oid sha256:dd64aba07e8746adb3af4fc58842f2353f1d75f2d93bdf728981a87ab557058a
 size 39398

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ccb4f4fa4dcfe5bc230fa2b68534e99c4447a88f31286dfb471650fb9f2ed51
+oid sha256:ab5744ac991c6a51cb31bf1cd57abcd6eb671ae5b35688f9556c3a2db19ad7be
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79f78716b356923e3a954e645268f3247781e92319c3c3c699c29edf2344335
+oid sha256:8846f3ddcbef0127b3a41ab63d4857dec886e87dd5c82dc9ff49a951919ee7aa
 size 14512

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": 0.0033651149747616375,
+  "epoch": 0.006730229949523275,
   "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": 460.789,
       "eval_steps_per_second": 115.351,
       "step": 3
+    },
+    {
+      "epoch": 0.00448681996634885,
+      "grad_norm": 0.005606319755315781,
+      "learning_rate": 8e-05,
+      "loss": 11.9338,
+      "step": 4
+    },
+    {
+      "epoch": 0.005608524957936063,
+      "grad_norm": 0.009023796766996384,
+      "learning_rate": 0.0001,
+      "loss": 11.9314,
+      "step": 5
+    },
+    {
+      "epoch": 0.006730229949523275,
+      "grad_norm": 0.01568673551082611,
+      "learning_rate": 0.00012,
+      "loss": 11.9317,
+      "step": 6
+    },
+    {
+      "epoch": 0.006730229949523275,
+      "eval_loss": 11.931279182434082,
+      "eval_runtime": 1.6377,
+      "eval_samples_per_second": 458.556,
+      "eval_steps_per_second": 114.792,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 738508800.0,
+  "total_flos": 1447477248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null