Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a313d509db7def5f49214f9d05b89c42300ce0ca3fd0d7a1b4c56154cf0a72db
+oid sha256:37296df7790e03d83312df3152295ea5675574fc24606e23051f92ba2a8785cd
 size 517931840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad0ef37ec0c5bff68abf0acafb2e524cd857e55490e94ef61cc44d1f7b08679
+oid sha256:ddcb0501b4cfee967f8db5bb4fa8fb92b655ff610b064b96b43d66b2ba0fdac4
 size 1035661434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b2c7bb39719c8f039a2a4dd5473921c41a834e3390491b2b93e9a2772ee802f
+oid sha256:a4c247dc7c4172df7c1d104b1da0eaec0df0b665cbc24707f3227675351f1df9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff7808903acfc88c8f83b83043a92f900db8f72ffc7d87d61c8ee1abceef7bc
+oid sha256:7ad5c996b0875772675f1bc75e15a0dbeb09c5ba7146d169befa6908149e4159
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08786417297160752,
+  "epoch": 0.10983021621450939,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -720,11 +720,189 @@
       "eval_steps_per_second": 19.053,
       "num_input_tokens_seen": 4194304000,
       "step": 4000
+    },
+    {
+      "epoch": 0.0889624751337526,
+      "grad_norm": 0.1839856207370758,
+      "learning_rate": 0.0008100000000000001,
+      "loss": 3.0862,
+      "num_input_tokens_seen": 4246732800,
+      "step": 4050
+    },
+    {
+      "epoch": 0.0900607772958977,
+      "grad_norm": 0.17331145703792572,
+      "learning_rate": 0.00082,
+      "loss": 3.087,
+      "num_input_tokens_seen": 4299161600,
+      "step": 4100
+    },
+    {
+      "epoch": 0.0911590794580428,
+      "grad_norm": 0.18384258449077606,
+      "learning_rate": 0.00083,
+      "loss": 3.076,
+      "num_input_tokens_seen": 4351590400,
+      "step": 4150
+    },
+    {
+      "epoch": 0.09225738162018789,
+      "grad_norm": 0.17061170935630798,
+      "learning_rate": 0.00084,
+      "loss": 3.0693,
+      "num_input_tokens_seen": 4404019200,
+      "step": 4200
+    },
+    {
+      "epoch": 0.09335568378233298,
+      "grad_norm": 0.18157647550106049,
+      "learning_rate": 0.00085,
+      "loss": 3.0698,
+      "num_input_tokens_seen": 4456448000,
+      "step": 4250
+    },
+    {
+      "epoch": 0.09445398594447808,
+      "grad_norm": 0.15678547322750092,
+      "learning_rate": 0.00086,
+      "loss": 3.064,
+      "num_input_tokens_seen": 4508876800,
+      "step": 4300
+    },
+    {
+      "epoch": 0.09555228810662317,
+      "grad_norm": 0.19118325412273407,
+      "learning_rate": 0.00087,
+      "loss": 3.0541,
+      "num_input_tokens_seen": 4561305600,
+      "step": 4350
+    },
+    {
+      "epoch": 0.09665059026876827,
+      "grad_norm": 0.17620691657066345,
+      "learning_rate": 0.00088,
+      "loss": 3.0532,
+      "num_input_tokens_seen": 4613734400,
+      "step": 4400
+    },
+    {
+      "epoch": 0.09774889243091336,
+      "grad_norm": 0.17351101338863373,
+      "learning_rate": 0.0008900000000000001,
+      "loss": 3.0549,
+      "num_input_tokens_seen": 4666163200,
+      "step": 4450
+    },
+    {
+      "epoch": 0.09884719459305845,
+      "grad_norm": 0.15183581411838531,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 3.0485,
+      "num_input_tokens_seen": 4718592000,
+      "step": 4500
+    },
+    {
+      "epoch": 0.09884719459305845,
+      "eval_loss": 2.9479379653930664,
+      "eval_runtime": 66.5611,
+      "eval_samples_per_second": 75.119,
+      "eval_steps_per_second": 18.78,
+      "num_input_tokens_seen": 4718592000,
+      "step": 4500
+    },
+    {
+      "epoch": 0.09994549675520355,
+      "grad_norm": 0.1681961864233017,
+      "learning_rate": 0.00091,
+      "loss": 3.0395,
+      "num_input_tokens_seen": 4771020800,
+      "step": 4550
+    },
+    {
+      "epoch": 0.10104379891734865,
+      "grad_norm": 0.17382557690143585,
+      "learning_rate": 0.00092,
+      "loss": 3.0371,
+      "num_input_tokens_seen": 4823449600,
+      "step": 4600
+    },
+    {
+      "epoch": 0.10214210107949374,
+      "grad_norm": 0.14377906918525696,
+      "learning_rate": 0.00093,
+      "loss": 3.0377,
+      "num_input_tokens_seen": 4875878400,
+      "step": 4650
+    },
+    {
+      "epoch": 0.10324040324163883,
+      "grad_norm": 0.1590214967727661,
+      "learning_rate": 0.00094,
+      "loss": 3.0305,
+      "num_input_tokens_seen": 4928307200,
+      "step": 4700
+    },
+    {
+      "epoch": 0.10433870540378393,
+      "grad_norm": 0.15563353896141052,
+      "learning_rate": 0.00095,
+      "loss": 3.0254,
+      "num_input_tokens_seen": 4980736000,
+      "step": 4750
+    },
+    {
+      "epoch": 0.10543700756592903,
+      "grad_norm": 0.16002103686332703,
+      "learning_rate": 0.00096,
+      "loss": 3.0222,
+      "num_input_tokens_seen": 5033164800,
+      "step": 4800
+    },
+    {
+      "epoch": 0.10653530972807411,
+      "grad_norm": 0.1406039148569107,
+      "learning_rate": 0.0009699999999999999,
+      "loss": 3.0185,
+      "num_input_tokens_seen": 5085593600,
+      "step": 4850
+    },
+    {
+      "epoch": 0.10763361189021921,
+      "grad_norm": 0.14609627425670624,
+      "learning_rate": 0.00098,
+      "loss": 3.0177,
+      "num_input_tokens_seen": 5138022400,
+      "step": 4900
+    },
+    {
+      "epoch": 0.1087319140523643,
+      "grad_norm": 0.16061657667160034,
+      "learning_rate": 0.00099,
+      "loss": 3.0137,
+      "num_input_tokens_seen": 5190451200,
+      "step": 4950
+    },
+    {
+      "epoch": 0.10983021621450939,
+      "grad_norm": 0.18423974514007568,
+      "learning_rate": 0.001,
+      "loss": 3.016,
+      "num_input_tokens_seen": 5242880000,
+      "step": 5000
+    },
+    {
+      "epoch": 0.10983021621450939,
+      "eval_loss": 2.9132862091064453,
+      "eval_runtime": 65.7163,
+      "eval_samples_per_second": 76.085,
+      "eval_steps_per_second": 19.021,
+      "num_input_tokens_seen": 5242880000,
+      "step": 5000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 4194304000,
+  "num_input_tokens_seen": 5242880000,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -739,7 +917,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.388686863859712e+18,
+  "total_flos": 2.98585857982464e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null