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:f936485fe4a1cc4cba365745259ba34d48f547914c25782f114345bc8aff4917
+oid sha256:992af3807f1ddde492d5d21ef8003dfe0acac62e56538c151e386def62e23ef9
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:765a1428de72f862cfc12a76798ebec3a3dc6508fe1471f9673917bed6d95a97
+oid sha256:7f06405c99ed4f51b5d3a971655d498026c6008bb37fac6876c897bbdc487098
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de640fa99e5941b21233304e139535faa7a366f48810e513a4ede28893ca34c7
+oid sha256:2724d1b00591b75da7d4b1beb6ec9510ce0c9f06d432df9cfd3bec7a246b509f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7910447761194028,
+  "epoch": 1.9701492537313432,
   "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": 15.065,
       "eval_steps_per_second": 1.95,
       "step": 90
+    },
+    {
+      "epoch": 1.8507462686567164,
+      "grad_norm": 0.6307412385940552,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.9657,
+      "step": 93
+    },
+    {
+      "epoch": 1.9104477611940298,
+      "grad_norm": 0.5744690895080566,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.8921,
+      "step": 96
+    },
+    {
+      "epoch": 1.9701492537313432,
+      "grad_norm": 0.6007259488105774,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 0.9583,
+      "step": 99
+    },
+    {
+      "epoch": 1.9701492537313432,
+      "eval_loss": 0.9787780046463013,
+      "eval_runtime": 5.6467,
+      "eval_samples_per_second": 15.053,
+      "eval_steps_per_second": 1.948,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1758163520493978e+17,
+  "total_flos": 1.2934388283919565e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null