Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebeffb2c037b50b65a6c0dee470a06e80bc04cb18fc25d36c6c23ebbfb1bfdb7
+oid sha256:c92b8ea1ab7aa1c3c704ca60e66275b713cae4225ae135b904f4c11a6b994994
 size 517931840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56670a00c0a6655472a5df0bad61f805ef42230ce33d41f768bab9a708635a97
+oid sha256:7a3f3c04ed042650af1b9c11df2cc35ac490889b1116ef774fd4222e5f41e410
 size 1035661434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b383a5a228123d48b81ff62301f8c357c6f3a9cd7484f11e193f37bbe5162530
+oid sha256:e5e2f21ad13dc4eb631067c76b1a1560519d302bc60e4e9cb00bba81ca70a316
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2af187ec456db07cec83217e48a58a7d4609355155eba34a029dc1dd312e2a7
+oid sha256:a234e8f8153fe3070553b0b2d9439870baa50cef586f11ec979ecf56399b8c74
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.37342273512933194,
+  "epoch": 0.3953887783722338,
   "eval_steps": 500,
-  "global_step": 17000,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3034,11 +3034,189 @@
       "eval_steps_per_second": 19.189,
       "num_input_tokens_seen": 17825792000,
       "step": 17000
+    },
+    {
+      "epoch": 0.374521037291477,
+      "grad_norm": 0.1361106038093567,
+      "learning_rate": 0.001,
+      "loss": 2.7342,
+      "num_input_tokens_seen": 17878220800,
+      "step": 17050
+    },
+    {
+      "epoch": 0.37561933945362214,
+      "grad_norm": 0.13839572668075562,
+      "learning_rate": 0.001,
+      "loss": 2.7259,
+      "num_input_tokens_seen": 17930649600,
+      "step": 17100
+    },
+    {
+      "epoch": 0.3767176416157672,
+      "grad_norm": 0.13055244088172913,
+      "learning_rate": 0.001,
+      "loss": 2.7306,
+      "num_input_tokens_seen": 17983078400,
+      "step": 17150
+    },
+    {
+      "epoch": 0.37781594377791233,
+      "grad_norm": 0.1444411724805832,
+      "learning_rate": 0.001,
+      "loss": 2.7315,
+      "num_input_tokens_seen": 18035507200,
+      "step": 17200
+    },
+    {
+      "epoch": 0.3789142459400574,
+      "grad_norm": 0.151028573513031,
+      "learning_rate": 0.001,
+      "loss": 2.7211,
+      "num_input_tokens_seen": 18087936000,
+      "step": 17250
+    },
+    {
+      "epoch": 0.38001254810220253,
+      "grad_norm": 0.15638011693954468,
+      "learning_rate": 0.001,
+      "loss": 2.7269,
+      "num_input_tokens_seen": 18140364800,
+      "step": 17300
+    },
+    {
+      "epoch": 0.3811108502643476,
+      "grad_norm": 0.1508658230304718,
+      "learning_rate": 0.001,
+      "loss": 2.7263,
+      "num_input_tokens_seen": 18192793600,
+      "step": 17350
+    },
+    {
+      "epoch": 0.38220915242649267,
+      "grad_norm": 0.13167701661586761,
+      "learning_rate": 0.001,
+      "loss": 2.7296,
+      "num_input_tokens_seen": 18245222400,
+      "step": 17400
+    },
+    {
+      "epoch": 0.3833074545886378,
+      "grad_norm": 0.14609253406524658,
+      "learning_rate": 0.001,
+      "loss": 2.7249,
+      "num_input_tokens_seen": 18297651200,
+      "step": 17450
+    },
+    {
+      "epoch": 0.38440575675078287,
+      "grad_norm": 0.13172782957553864,
+      "learning_rate": 0.001,
+      "loss": 2.7252,
+      "num_input_tokens_seen": 18350080000,
+      "step": 17500
+    },
+    {
+      "epoch": 0.38440575675078287,
+      "eval_loss": 2.630176544189453,
+      "eval_runtime": 66.0667,
+      "eval_samples_per_second": 75.681,
+      "eval_steps_per_second": 18.92,
+      "num_input_tokens_seen": 18350080000,
+      "step": 17500
+    },
+    {
+      "epoch": 0.385504058912928,
+      "grad_norm": 0.149306520819664,
+      "learning_rate": 0.001,
+      "loss": 2.7245,
+      "num_input_tokens_seen": 18402508800,
+      "step": 17550
+    },
+    {
+      "epoch": 0.38660236107507306,
+      "grad_norm": 0.14191772043704987,
+      "learning_rate": 0.001,
+      "loss": 2.7204,
+      "num_input_tokens_seen": 18454937600,
+      "step": 17600
+    },
+    {
+      "epoch": 0.3877006632372182,
+      "grad_norm": 0.13731072843074799,
+      "learning_rate": 0.001,
+      "loss": 2.7243,
+      "num_input_tokens_seen": 18507366400,
+      "step": 17650
+    },
+    {
+      "epoch": 0.38879896539936326,
+      "grad_norm": 0.1466369777917862,
+      "learning_rate": 0.001,
+      "loss": 2.7262,
+      "num_input_tokens_seen": 18559795200,
+      "step": 17700
+    },
+    {
+      "epoch": 0.38989726756150833,
+      "grad_norm": 0.13290658593177795,
+      "learning_rate": 0.001,
+      "loss": 2.7314,
+      "num_input_tokens_seen": 18612224000,
+      "step": 17750
+    },
+    {
+      "epoch": 0.39099556972365346,
+      "grad_norm": 0.13785040378570557,
+      "learning_rate": 0.001,
+      "loss": 2.7252,
+      "num_input_tokens_seen": 18664652800,
+      "step": 17800
+    },
+    {
+      "epoch": 0.39209387188579853,
+      "grad_norm": 0.13384000957012177,
+      "learning_rate": 0.001,
+      "loss": 2.7321,
+      "num_input_tokens_seen": 18717081600,
+      "step": 17850
+    },
+    {
+      "epoch": 0.39319217404794365,
+      "grad_norm": 0.14927875995635986,
+      "learning_rate": 0.001,
+      "loss": 2.7236,
+      "num_input_tokens_seen": 18769510400,
+      "step": 17900
+    },
+    {
+      "epoch": 0.3942904762100887,
+      "grad_norm": 0.13494938611984253,
+      "learning_rate": 0.001,
+      "loss": 2.7234,
+      "num_input_tokens_seen": 18821939200,
+      "step": 17950
+    },
+    {
+      "epoch": 0.3953887783722338,
+      "grad_norm": 0.15054813027381897,
+      "learning_rate": 0.001,
+      "loss": 2.7236,
+      "num_input_tokens_seen": 18874368000,
+      "step": 18000
+    },
+    {
+      "epoch": 0.3953887783722338,
+      "eval_loss": 2.62626051902771,
+      "eval_runtime": 65.3965,
+      "eval_samples_per_second": 76.457,
+      "eval_steps_per_second": 19.114,
+      "num_input_tokens_seen": 18874368000,
+      "step": 18000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 17825792000,
+  "num_input_tokens_seen": 18874368000,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -3053,7 +3231,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0151919171403776e+19,
+  "total_flos": 1.0749090887368704e+19,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null