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:ed1041d1356023f75f774876be10c88b9e5bd68772c12e9f363d22d125cb82ca
+oid sha256:a35b79f7523d6182e7d7797f6cc4ed7cc1e54c038bc6e82e750bdfa935a953bd
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a031febeff039fc9d82545109dcde0dbfd300d1e08892393534802a00e41dded
+oid sha256:93886c11b35c9386b12420559fe8465698db2a4d2d12bcab6f33184c7f4a451f
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
+oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
 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": 0.0022087244616234127,
+  "epoch": 0.004417448923246825,
   "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": 55.211,
       "eval_steps_per_second": 55.211,
       "step": 3
+    },
+    {
+      "epoch": 0.0029449659488312166,
+      "grad_norm": 0.028326112776994705,
+      "learning_rate": 8e-05,
+      "loss": 11.9315,
+      "step": 4
+    },
+    {
+      "epoch": 0.003681207436039021,
+      "grad_norm": 0.02255975268781185,
+      "learning_rate": 0.0001,
+      "loss": 11.9335,
+      "step": 5
+    },
+    {
+      "epoch": 0.004417448923246825,
+      "grad_norm": 0.023017868399620056,
+      "learning_rate": 0.00012,
+      "loss": 11.936,
+      "step": 6
+    },
+    {
+      "epoch": 0.004417448923246825,
+      "eval_loss": 11.930936813354492,
+      "eval_runtime": 5.2221,
+      "eval_samples_per_second": 54.767,
+      "eval_steps_per_second": 54.767,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2248409088.0,
+  "total_flos": 4496818176.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null