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:d53ba7ae53cf6f135d67937e1ace44070f373b16dd32e2181a8a8339c0c77bd1
+oid sha256:86e54584c9fd0487ec7e4f14e496b28d5b067151048db5b0fee9d7e85a4a68c8
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5802926d3099de012a59c35be7971098dba6fcde771bc6ea78119fa13654a764
+oid sha256:00878f593dca7653794211e8e4f6b8d4ce15f86a30e31646b3b30de59e656d9b
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd8936daf23c7cbb86e7a823d198467d57e6721b6ccaa5c75d81f7d8d3a5a0e
+oid sha256:c58b0f87d75899bb7278d92ca01276981514ff3189f6f8b4388d4cdea082d8ad
 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": 0.005263157894736842,
+  "epoch": 0.010526315789473684,
   "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": 103.165,
       "eval_steps_per_second": 51.582,
       "step": 3
+    },
+    {
+      "epoch": 0.007017543859649123,
+      "grad_norm": 6.407444953918457,
+      "learning_rate": 8e-05,
+      "loss": 7.4857,
+      "step": 4
+    },
+    {
+      "epoch": 0.008771929824561403,
+      "grad_norm": 6.00010347366333,
+      "learning_rate": 0.0001,
+      "loss": 6.5114,
+      "step": 5
+    },
+    {
+      "epoch": 0.010526315789473684,
+      "grad_norm": 6.50211763381958,
+      "learning_rate": 0.00012,
+      "loss": 7.7122,
+      "step": 6
+    },
+    {
+      "epoch": 0.010526315789473684,
+      "eval_loss": 1.8417414426803589,
+      "eval_runtime": 2.4088,
+      "eval_samples_per_second": 99.637,
+      "eval_steps_per_second": 49.818,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10084018028544.0,
+  "total_flos": 19637298266112.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null