Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cec4a58265007f7afb954c6a9f36b12363a2748a54f2e06adfcc70cf1bd3eea
+oid sha256:5b65047e192baf9cfd222ae4b9798f57171f0c91bd72c92de7f11c517dd656c9
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd7bde69d2d64adf8d945ca3a7ddf51e14169ebdde33aa92409b79587b24585
+oid sha256:b0e37db546ef652757c2500c7b31b90d87c190949e3fd391ea2e6ec66b14f4d5
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:623f4ff822c667b12ddbc69b1d737a8b191d5cf0e9809ed6c4031104e64d27d4
+oid sha256:16f8dce4ea8db55fab98810852c3b7d6da325bbb69e21644a5658ad81a5d8213
 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": 0.008379888268156424,
+  "epoch": 0.01675977653631285,
   "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": 20.84,
       "eval_steps_per_second": 10.489,
       "step": 3
+    },
+    {
+      "epoch": 0.0111731843575419,
+      "grad_norm": 3.740717887878418,
+      "learning_rate": 8e-05,
+      "loss": 9.0674,
+      "step": 4
+    },
+    {
+      "epoch": 0.013966480446927373,
+      "grad_norm": 3.150239944458008,
+      "learning_rate": 0.0001,
+      "loss": 8.5266,
+      "step": 5
+    },
+    {
+      "epoch": 0.01675977653631285,
+      "grad_norm": 3.9240503311157227,
+      "learning_rate": 0.00012,
+      "loss": 8.6384,
+      "step": 6
+    },
+    {
+      "epoch": 0.01675977653631285,
+      "eval_loss": 2.2556746006011963,
+      "eval_runtime": 11.1555,
+      "eval_samples_per_second": 13.536,
+      "eval_steps_per_second": 6.813,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 855841607516160.0,
+  "total_flos": 1711683215032320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null