Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242be712bcb3c7327aa7dfe0f461bf51718192a3c2692e51ac2f63eb2faa5c33
+oid sha256:bdb20148addd4b10c5358624ce2f35461ceb245143af0f9b446505ba790b756b
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ff850ad9acade3a35105fcdddc1e95fde0c9d0a096975a5d2a6f0ae4d7fb954
+oid sha256:eeaa877ec6fdc8173ce0cd87b831cae5028213b8fdb553ea3c6aaa44fa1c7ba6
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b04b91ebb84c2b2ce59f23243bcad840c62f3f58a7479270a8b0cda9da80b109
+oid sha256:1e177607e9900e964a62c96b0923e9c25ec65b2d179187fe73b8403d497bebb1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
+oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013753581661891117,
+  "epoch": 0.015128939828080229,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 37.11,
       "eval_steps_per_second": 4.64,
       "step": 90
+    },
+    {
+      "epoch": 0.014212034383954155,
+      "grad_norm": 0.24415625631809235,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.3288,
+      "step": 93
+    },
+    {
+      "epoch": 0.014670487106017193,
+      "grad_norm": 0.09298162907361984,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0904,
+      "step": 96
+    },
+    {
+      "epoch": 0.015128939828080229,
+      "grad_norm": 0.007296608295291662,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.1468,
+      "step": 99
+    },
+    {
+      "epoch": 0.015128939828080229,
+      "eval_loss": 0.2796213924884796,
+      "eval_runtime": 296.5122,
+      "eval_samples_per_second": 37.169,
+      "eval_steps_per_second": 4.647,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.882117805539328e+16,
+  "total_flos": 3.170329586093261e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null