Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f50aff06f98dbb1489e94e53e8e155ed14da3f1281f7170ce6fc6857625e17a
+oid sha256:fb392aeff661116a9ac6e35b7240669e981f96d57f2a3f50b5ad57ac3050ee43
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74936d4495ba704d080266e01575c803a734984e6bc8b527a37004d9950de44c
+oid sha256:ba20f2e7798a24f9b50a3ad60666738af1896754e1be54a175f41858273b0168
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d861c6a390a32db99b32b21fb254f11ccec4040fa92f6643a342e1e89e9da6
+oid sha256:11e92c2bededb678e5d9d037dd1170e39f9f1222223448f176b879104f318b24
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee9b46319ea183bdb1ff6aeb8d91de1c0cca6ddeb92ade57ebcc69a8fa1ff6e5
+oid sha256:33c4d38cf9571771c75f6b2d0eb4efb6e1f5b169e9157086fbe55fbf58d51b76
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d4024038f7af0e004b66c02d28c6817f03f07a611fdf206029711baf11d4592
+oid sha256:9cd1565c336730ad1fa1aa4882bc3240b7d664c1bfe9faf9749db55bcd315b45
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a5e71e3e8aa7ac8635fed62601d4dab5448c22faf71fdd95b83793fdedfcc4
+oid sha256:6dde576991a63cd51e44433c1fc13f7c1f7ec2bff967aa5fec1a8b2a433c1c92
 size 14960

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": 0.03889369057908384,
+  "epoch": 0.04278305963699222,
   "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": 118.069,
       "eval_steps_per_second": 3.696,
       "step": 90
+    },
+    {
+      "epoch": 0.04019014693171997,
+      "grad_norm": 0.984551191329956,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.4686,
+      "step": 93
+    },
+    {
+      "epoch": 0.04148660328435609,
+      "grad_norm": 1.0442090034484863,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.5048,
+      "step": 96
+    },
+    {
+      "epoch": 0.04278305963699222,
+      "grad_norm": 0.8811266422271729,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.4768,
+      "step": 99
+    },
+    {
+      "epoch": 0.04278305963699222,
+      "eval_loss": 1.4746631383895874,
+      "eval_runtime": 132.1003,
+      "eval_samples_per_second": 118.009,
+      "eval_steps_per_second": 3.694,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.854041921079214e+17,
+  "total_flos": 3.1385413385977856e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null