Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:554a05c79b6970f05612f20a53fb142204c7ccd5808ae60149536d4c55264da9
+oid sha256:9032e9a88f6f9c79f637ab75f83694a2dc476cbc777aabf84fab1ceac1c70e1f
 size 268290900

run-4/checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f905aa4e0351f726703bf94a11837bc1bc6a52dc919b464b433bb31ee44cf05
+oid sha256:417f67bfc777c996b35c8996ff62c52ec34d71e7a766e99077134c8e94a8f85b
 size 268290900

run-4/checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0f2a244de8293a04ffe52e6d12be4190e593992609ab16af5335db404902310
+oid sha256:aa48a0c978c6a7ede2f05dfd7e1a4fdfa87e493dfd4351367eab5fe63f91142a
 size 536643898

run-4/checkpoint-1500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4150b40cdd095f99e6d506db714a6c0a9a316d6b4d021acbfec8d198c96919
+oid sha256:1c10319269a5ccb2640eed78049edda0fca1ea40d757f64b6ab5474fe9e926f9
 size 14244

run-4/checkpoint-1500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71453465aad25f4c5a0a948496c64b1f74df850abda497954afe3695c00756ee
+oid sha256:55c8d3ce0734337fc0c187ca5543b4c70ca45d996531f199209b3a0c2a798109
 size 1064

run-4/checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5d2fff8a65a6470ff21893289269130aa490c201d7c1e86a6b03304d6d7dd8
-size 4728
+oid sha256:09c1d2b3517a81c25cfd3dc4720ca0f5c5cd50449810325441209751db6b15be
+size 5176

run-5/checkpoint-500/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.41.1",
   "vocab_size": 30522
 }

run-5/checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c24b0a4a8801f00062afb827eb49d3d1a5b189f65890c2bf2e8b900738912d9c
+oid sha256:9032e9a88f6f9c79f637ab75f83694a2dc476cbc777aabf84fab1ceac1c70e1f
 size 268290900

run-5/checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2747916ed8ac1c16a5e74b2324d8c38bfccaba7207dae222205f1e3343c41964
+oid sha256:d4663de9ae3e603da38c925519eb450716b9756d7e66f8d52d633f08329dad88
 size 536643898

run-5/checkpoint-500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8174c1d6ac2627de77161655e4e20ef37d9f2235e2e7c4adc0da0d4e0e14b6d
+oid sha256:b9fb2a0dfb1b0ccef3590fe01e9bd16b6db86f247cc9c7e77290c217a53bac20
 size 14244

run-5/checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1264523e958cf7990dc5f42d876cc12129475c4603804cf66868aaf25c2c24
+oid sha256:98041bd7cae455426e290a1a0ee683bd5dd30893f7451fec3a464ae8995b17e4
 size 1064

run-5/checkpoint-500/tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

run-5/checkpoint-500/trainer_state.json

@@ -10,31 +10,44 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6558064516129032,
-      "eval_loss": 0.3044227957725525,
-      "eval_runtime": 1.3634,
-      "eval_samples_per_second": 2273.787,
-      "eval_steps_per_second": 47.676,
+      "eval_accuracy": 0.584516129032258,
+      "eval_loss": 0.19766665995121002,
+      "eval_runtime": 1.3839,
+      "eval_samples_per_second": 2239.966,
+      "eval_steps_per_second": 46.967,
       "step": 318
     },
     {
-      "epoch": 1.57,
-      "learning_rate": 1.371069182389937e-05,
-      "loss": 0.4709,
+      "epoch": 1.5723270440251573,
+      "grad_norm": 0.5089908242225647,
+      "learning_rate": 1.650593990216632e-05,
+      "loss": 0.318,
       "step": 500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1590,
+  "max_steps": 2862,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 9,
   "save_steps": 500,
-  "total_flos": 129219778448376.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 130072209152340.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.12690688175028453,
-    "num_train_epochs": 5,
-    "temperature": 3
+    "alpha": 0.18633073638587916,
+    "num_train_epochs": 9,
+    "temperature": 12
   }
 }

run-5/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fa1c7452d85339003243159437eb829c186323cd1ac6c8ab11eba049b601da9
-size 4728
+oid sha256:2b710d040c65b4e79eb6b061acc6db3a0384cdfac91c487c974101b5770343aa
+size 5176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09c1d2b3517a81c25cfd3dc4720ca0f5c5cd50449810325441209751db6b15be
+oid sha256:2b710d040c65b4e79eb6b061acc6db3a0384cdfac91c487c974101b5770343aa
 size 5176