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:e03f39de671b0dbdd3f7c1eecd651e7c494b695e23e5a91e2b6e5510ed370a90
+oid sha256:79b505f3aa54c15b17c2d918bab8b1bb08893568fe3762dbf43a0d95faa89d7f
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9605442b54b0f76343325dc74af903b3d5384d9b82b866362c40da899cd54b73
+oid sha256:c110479f74b0bad0f2216846702b9aad6b89cf1fef4d4900bef3a542e25c98f3
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fe0bc52f18109202325f428968e807a0f8b4cc05e9b0dd02c5bed472205dc5c
+oid sha256:e60e08514843cd33eaf7ceebe02437d99ec8a00041ba6418bb40b89a1c5cd556
 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": 0.0003080161195102544,
+  "epoch": 0.0006160322390205088,
   "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": 6.409,
       "eval_steps_per_second": 3.205,
       "step": 3
+    },
+    {
+      "epoch": 0.00041068815934700584,
+      "grad_norm": 0.31777092814445496,
+      "learning_rate": 8e-05,
+      "loss": 2.0824,
+      "step": 4
+    },
+    {
+      "epoch": 0.0005133601991837573,
+      "grad_norm": 0.24618875980377197,
+      "learning_rate": 0.0001,
+      "loss": 2.2182,
+      "step": 5
+    },
+    {
+      "epoch": 0.0006160322390205088,
+      "grad_norm": 0.2700459361076355,
+      "learning_rate": 0.00012,
+      "loss": 2.4521,
+      "step": 6
+    },
+    {
+      "epoch": 0.0006160322390205088,
+      "eval_loss": 2.1164493560791016,
+      "eval_runtime": 639.304,
+      "eval_samples_per_second": 6.415,
+      "eval_steps_per_second": 3.208,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 617621263220736.0,
+  "total_flos": 1235242526441472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null