Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f7d44626f0c8060fc772ba0e3d528b739731ca320d4039b79667735454db634
+oid sha256:98cbe443404271992d0189cef878edd7dbba25522bc6e689d23f1b7f62c91131
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e950c08e348b928134a78ec5ad43a977454f27c678ade8a6d4513b92266b740b
+oid sha256:2df0189c82fe014622e8696ae9ebe65051b5b3b04496fc669f43341898c70d66
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f93ea690cd2884dba1d0f84fad41aec8e0ad383f3c9c463e454e02e204c76e5
+oid sha256:56c02568f27f39db1b820349b1a7c05fb395c708ccb27167899d5f132f0fe1d4
 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": 0.00027871974729409577,
+  "epoch": 0.0005574394945881915,
   "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": 94.158,
       "eval_steps_per_second": 47.079,
       "step": 3
+    },
+    {
+      "epoch": 0.00037162632972546103,
+      "grad_norm": 62.255516052246094,
+      "learning_rate": 8e-05,
+      "loss": 13.6484,
+      "step": 4
+    },
+    {
+      "epoch": 0.0004645329121568263,
+      "grad_norm": 68.01496887207031,
+      "learning_rate": 0.0001,
+      "loss": 15.8262,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005574394945881915,
+      "grad_norm": 42.891239166259766,
+      "learning_rate": 0.00012,
+      "loss": 13.0994,
+      "step": 6
+    },
+    {
+      "epoch": 0.0005574394945881915,
+      "eval_loss": 3.4298434257507324,
+      "eval_runtime": 47.8312,
+      "eval_samples_per_second": 94.75,
+      "eval_steps_per_second": 47.375,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 28511783878656.0,
+  "total_flos": 54830353612800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null