Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74f96606372a5994a100853ff984c8fb11894bffa30a719e8da48a46fdb2fa71
+oid sha256:dc054a53ac2c5b022b9508ecda5f5e3e1c63e33e4c80532d2ac1d0a1e43f25b9
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:444eb3a7ee2c92e7f1083fb6891f4ef787426a3757f8afd0ba3a572510147363
+oid sha256:778d8eb6003105677c267cdc05f97aa5ea02e04d0a7aabbb94cd0189c2f165ea
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9264abfa6d2cc5145363bf71d2fb16332b1ac4e60642a70827881d9a447c36a4
+oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
 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": 8.426670411853516e-05,
+  "epoch": 0.00016853340823707032,
   "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": 304.141,
       "eval_steps_per_second": 152.071,
       "step": 3
+    },
+    {
+      "epoch": 0.00011235560549138022,
+      "grad_norm": 0.7071318030357361,
+      "learning_rate": 8e-05,
+      "loss": 44.4346,
+      "step": 4
+    },
+    {
+      "epoch": 0.00014044450686422527,
+      "grad_norm": 0.6881616711616516,
+      "learning_rate": 0.0001,
+      "loss": 44.4856,
+      "step": 5
+    },
+    {
+      "epoch": 0.00016853340823707032,
+      "grad_norm": 0.747654378414154,
+      "learning_rate": 0.00012,
+      "loss": 44.4517,
+      "step": 6
+    },
+    {
+      "epoch": 0.00016853340823707032,
+      "eval_loss": 11.112412452697754,
+      "eval_runtime": 49.4184,
+      "eval_samples_per_second": 303.328,
+      "eval_steps_per_second": 151.664,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 50635210752.0,
+  "total_flos": 96448020480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null