Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ba2fa27850ccf6ed4e05a6a9c4099afd1656f0bc266eadf1b5c97a1a9acaaa
+oid sha256:0335e9e2dec37347411ac34f4b74d36a612519946e1fb6f40a5d085cd967d481
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fadc7d377dfef603d7d0a942047e8261bbf5740b2236bb76d798284b7bb9090b
+oid sha256:8de9d2189d87ce80d83621fdf97af13d51fd436678aeeb5258b371f931152091
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47564a35447afa07e3b75bf0a6236829d89af29c9827ae45b88f9f27041e767e
+oid sha256:54759f812b77812db83ee31768a28f59a8e0f72bbef4c68914dba7ad2bdf3f47
 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": 0.000507292327203551,
+  "epoch": 0.001014584654407102,
   "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": 29.228,
       "eval_steps_per_second": 14.614,
       "step": 3
+    },
+    {
+      "epoch": 0.0006763897696047348,
+      "grad_norm": 8.164813041687012,
+      "learning_rate": 8e-05,
+      "loss": 6.3247,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008454872120059184,
+      "grad_norm": 8.150789260864258,
+      "learning_rate": 0.0001,
+      "loss": 6.4343,
+      "step": 5
+    },
+    {
+      "epoch": 0.001014584654407102,
+      "grad_norm": 7.140324592590332,
+      "learning_rate": 0.00012,
+      "loss": 5.5998,
+      "step": 6
+    },
+    {
+      "epoch": 0.001014584654407102,
+      "eval_loss": 5.347555637359619,
+      "eval_runtime": 85.3388,
+      "eval_samples_per_second": 29.178,
+      "eval_steps_per_second": 14.589,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 377083649851392.0,
+  "total_flos": 719886967898112.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null