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:bc5d49020560db5993e673613ad48e834ff46a454f003bd314aae83ba09551a6
+oid sha256:c2b2da141ae60812788f204a6329980072afdc0e419f1cc7de3eff5d59fdd750
 size 604317736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:779764423264b1e74aaff66a0ce8366c6958ef2164db81fa65bafe2c0b568843
+oid sha256:dd90c2773f839fa4e5003f2889daf4848131d208b1a267381c9bf09108c18ada
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b173ac9ab56406e53f02ac343bf22d13dc84cb35b451121151594928dcc2f4cd
+oid sha256:09acce823b858db1a079a05549bd8528f2fec468928dba778f7e8bdddcd10eea
 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": 3.8797785939682375e-05,
+  "epoch": 7.759557187936475e-05,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,35 @@
       "eval_samples_per_second": 18.236,
       "eval_steps_per_second": 9.118,
       "step": 3
+    },
+    {
+      "epoch": 5.173038125290983e-05,
+      "grad_norm": 1.284034013748169,
+      "learning_rate": 8e-05,
+      "loss": 1.4316,
+      "step": 4
+    },
+    {
+      "epoch": 6.46629765661373e-05,
+      "grad_norm": 1.3621246814727783,
+      "learning_rate": 0.0001,
+      "loss": 1.2137,
+      "step": 5
+    },
+    {
+      "epoch": 7.759557187936475e-05,
+      "grad_norm": 1.5063856840133667,
+      "learning_rate": 0.00012,
+      "loss": 1.3861,
+      "step": 6
+    },
+    {
+      "epoch": 7.759557187936475e-05,
+      "eval_loss": 1.1301480531692505,
+      "eval_runtime": 1801.8138,
+      "eval_samples_per_second": 18.07,
+      "eval_steps_per_second": 9.035,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -55,7 +84,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 488620242763776.0,
+  "total_flos": 977240485527552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null