Training in progress, step 102, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43bb5a29d334edbc3d32a698dd4e9aff97d5f6d6e815b2aaf90cb0cc29849d64
+oid sha256:8f48e5e504da172c01e6ee3da031e8a9cae7d2213f5cb8705cf8cc99dc402c40
 size 692136856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eb8e128771e16ec08f4fe017fd8d46665043ad4ca09b570f14b1e8bb18dabf2
+oid sha256:edaa271176ce862e004df1f0dc773f6ce9648c87c722df370b11c98cad47b292
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa42479a448d19a558a303ea6bb44fbbe582f6a25a171397769feee5dda3588
+oid sha256:b472766fb64a3faca824302324f58abb5e35dea39174d7a492c6d7c52b86b41c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57465ffa9dc280f2ea6034fe61064b0208bf36c7b5f569218c0e1296778ee099
+oid sha256:baea37709b071cdabc5712824dc3f783ecd30d18a1e0d85c4d56cfebfa22b7e0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004581901489117984,
+  "epoch": 0.006872852233676976,
   "eval_steps": 34,
-  "global_step": 68,
+  "global_step": 102,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -185,6 +185,98 @@
       "eval_samples_per_second": 14.03,
       "eval_steps_per_second": 1.754,
       "step": 68
+    },
+    {
+      "epoch": 0.004649282393369719,
+      "grad_norm": 0.7278714776039124,
+      "learning_rate": 4.7229269307953235e-05,
+      "loss": 0.741,
+      "step": 69
+    },
+    {
+      "epoch": 0.004851425106124924,
+      "grad_norm": 0.9090484380722046,
+      "learning_rate": 4.694636022946012e-05,
+      "loss": 0.8075,
+      "step": 72
+    },
+    {
+      "epoch": 0.00505356781888013,
+      "grad_norm": 0.8673194050788879,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.8395,
+      "step": 75
+    },
+    {
+      "epoch": 0.005255710531635335,
+      "grad_norm": 0.7307804822921753,
+      "learning_rate": 4.6342266598556814e-05,
+      "loss": 0.7995,
+      "step": 78
+    },
+    {
+      "epoch": 0.005457853244390539,
+      "grad_norm": 0.9184255003929138,
+      "learning_rate": 4.6021434819815555e-05,
+      "loss": 0.8318,
+      "step": 81
+    },
+    {
+      "epoch": 0.005659995957145745,
+      "grad_norm": 0.7924419045448303,
+      "learning_rate": 4.568832711511125e-05,
+      "loss": 0.8095,
+      "step": 84
+    },
+    {
+      "epoch": 0.00586213866990095,
+      "grad_norm": 0.7330142259597778,
+      "learning_rate": 4.534313800996299e-05,
+      "loss": 0.7674,
+      "step": 87
+    },
+    {
+      "epoch": 0.006064281382656155,
+      "grad_norm": 0.7591224908828735,
+      "learning_rate": 4.498606908508754e-05,
+      "loss": 0.8409,
+      "step": 90
+    },
+    {
+      "epoch": 0.006266424095411361,
+      "grad_norm": 0.7741730213165283,
+      "learning_rate": 4.46173288586818e-05,
+      "loss": 0.8541,
+      "step": 93
+    },
+    {
+      "epoch": 0.006468566808166565,
+      "grad_norm": 0.7202086448669434,
+      "learning_rate": 4.4237132664654154e-05,
+      "loss": 0.85,
+      "step": 96
+    },
+    {
+      "epoch": 0.0066707095209217705,
+      "grad_norm": 0.7738878726959229,
+      "learning_rate": 4.384570252687542e-05,
+      "loss": 0.8571,
+      "step": 99
+    },
+    {
+      "epoch": 0.006872852233676976,
+      "grad_norm": 0.7431773543357849,
+      "learning_rate": 4.344326702952326e-05,
+      "loss": 0.8264,
+      "step": 102
+    },
+    {
+      "epoch": 0.006872852233676976,
+      "eval_loss": 0.8239989280700684,
+      "eval_runtime": 1781.4353,
+      "eval_samples_per_second": 14.031,
+      "eval_steps_per_second": 1.754,
+      "step": 102
     }
   ],
   "logging_steps": 3,
@@ -204,7 +296,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.56256665814958e+16,
+  "total_flos": 1.4343849987224371e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null