Training in progress, step 152000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aa167c9a5844d6681ba1dc14f63075aa36230ac204c46518d95f15b6b331648
+oid sha256:d6742b674b0d53e2c3daed10497d7535a63d9e9f7f594d41925fa37702bc1094
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:057a4f093c9de5777e5441d6b9da2167846fe2aefc774bd7c5cdbfdb398816ee
+oid sha256:eab29f7de023579ff77f6510ad0f7600d1dadaeaa609fc84656241739c587bc8
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da1b6cbd580084d771f001ae42a7f74ff98618b0c8c6b15e4846f9625430ea88
+oid sha256:10363df25df4a89f891174d636e331bcdc2893b7259219b00bec7140fc37ee6b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9f202c0bf8bee1f7d5bad95c982f28f4e3c671f59536778571fdd36b98c7601
+oid sha256:4ae8b4289a05289ec5bdbf9ddf513572ea179aa9b7d8e7afc52b70d2964dfe0f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.3169262894591065,
+  "epoch": 3.338892347780364,
   "eval_steps": 500,
-  "global_step": 151000,
+  "global_step": 152000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -26886,11 +26886,189 @@
       "eval_steps_per_second": 15.519,
       "num_input_tokens_seen": 84922496000,
       "step": 151000
+    },
+    {
+      "epoch": 3.3180245923751692,
+      "grad_norm": 0.09862314164638519,
+      "learning_rate": 0.0001,
+      "loss": 2.3591,
+      "num_input_tokens_seen": 84974923744,
+      "step": 151050
+    },
+    {
+      "epoch": 3.3191228952912324,
+      "grad_norm": 0.09108031541109085,
+      "learning_rate": 0.0001,
+      "loss": 2.348,
+      "num_input_tokens_seen": 85027352544,
+      "step": 151100
+    },
+    {
+      "epoch": 3.320221198207295,
+      "grad_norm": 0.10582481324672699,
+      "learning_rate": 0.0001,
+      "loss": 2.3405,
+      "num_input_tokens_seen": 85079779360,
+      "step": 151150
+    },
+    {
+      "epoch": 3.321319501123358,
+      "grad_norm": 0.09384915232658386,
+      "learning_rate": 0.0001,
+      "loss": 2.3497,
+      "num_input_tokens_seen": 85132203008,
+      "step": 151200
+    },
+    {
+      "epoch": 3.322417804039421,
+      "grad_norm": 0.09305764734745026,
+      "learning_rate": 0.0001,
+      "loss": 2.3537,
+      "num_input_tokens_seen": 85184631808,
+      "step": 151250
+    },
+    {
+      "epoch": 3.3235161069554837,
+      "grad_norm": 0.09376391023397446,
+      "learning_rate": 0.0001,
+      "loss": 2.345,
+      "num_input_tokens_seen": 85237060608,
+      "step": 151300
+    },
+    {
+      "epoch": 3.3246144098715464,
+      "grad_norm": 0.09613306075334549,
+      "learning_rate": 0.0001,
+      "loss": 2.3462,
+      "num_input_tokens_seen": 85289487488,
+      "step": 151350
+    },
+    {
+      "epoch": 3.3257127127876096,
+      "grad_norm": 0.09579232335090637,
+      "learning_rate": 0.0001,
+      "loss": 2.3522,
+      "num_input_tokens_seen": 85341909344,
+      "step": 151400
+    },
+    {
+      "epoch": 3.3268110157036723,
+      "grad_norm": 0.08879666030406952,
+      "learning_rate": 0.0001,
+      "loss": 2.353,
+      "num_input_tokens_seen": 85394338144,
+      "step": 151450
+    },
+    {
+      "epoch": 3.327909318619735,
+      "grad_norm": 0.09744927287101746,
+      "learning_rate": 0.0001,
+      "loss": 2.3521,
+      "num_input_tokens_seen": 85446766432,
+      "step": 151500
+    },
+    {
+      "epoch": 3.327909318619735,
+      "eval_loss": 2.26111102104187,
+      "eval_runtime": 79.9827,
+      "eval_samples_per_second": 62.514,
+      "eval_steps_per_second": 15.628,
+      "num_input_tokens_seen": 85446766432,
+      "step": 151500
+    },
+    {
+      "epoch": 3.329007621535798,
+      "grad_norm": 0.0889928862452507,
+      "learning_rate": 0.0001,
+      "loss": 2.3436,
+      "num_input_tokens_seen": 85499195232,
+      "step": 151550
+    },
+    {
+      "epoch": 3.330105924451861,
+      "grad_norm": 0.09036596864461899,
+      "learning_rate": 0.0001,
+      "loss": 2.3525,
+      "num_input_tokens_seen": 85551624032,
+      "step": 151600
+    },
+    {
+      "epoch": 3.331204227367924,
+      "grad_norm": 0.09018707275390625,
+      "learning_rate": 0.0001,
+      "loss": 2.3397,
+      "num_input_tokens_seen": 85604051680,
+      "step": 151650
+    },
+    {
+      "epoch": 3.332302530283987,
+      "grad_norm": 0.09039066731929779,
+      "learning_rate": 0.0001,
+      "loss": 2.3529,
+      "num_input_tokens_seen": 85656480480,
+      "step": 151700
+    },
+    {
+      "epoch": 3.3334008332000495,
+      "grad_norm": 0.09161881357431412,
+      "learning_rate": 0.0001,
+      "loss": 2.3521,
+      "num_input_tokens_seen": 85708908800,
+      "step": 151750
+    },
+    {
+      "epoch": 3.3344991361161127,
+      "grad_norm": 0.09359107166528702,
+      "learning_rate": 0.0001,
+      "loss": 2.3535,
+      "num_input_tokens_seen": 85761337600,
+      "step": 151800
+    },
+    {
+      "epoch": 3.3355974390321754,
+      "grad_norm": 0.09596438705921173,
+      "learning_rate": 0.0001,
+      "loss": 2.3507,
+      "num_input_tokens_seen": 85813766400,
+      "step": 151850
+    },
+    {
+      "epoch": 3.3366957419482386,
+      "grad_norm": 0.09060530364513397,
+      "learning_rate": 0.0001,
+      "loss": 2.3488,
+      "num_input_tokens_seen": 85866195200,
+      "step": 151900
+    },
+    {
+      "epoch": 3.3377940448643013,
+      "grad_norm": 0.09371770173311234,
+      "learning_rate": 0.0001,
+      "loss": 2.3452,
+      "num_input_tokens_seen": 85918618144,
+      "step": 151950
+    },
+    {
+      "epoch": 3.338892347780364,
+      "grad_norm": 0.10104481130838394,
+      "learning_rate": 0.0001,
+      "loss": 2.3474,
+      "num_input_tokens_seen": 85971046944,
+      "step": 152000
+    },
+    {
+      "epoch": 3.338892347780364,
+      "eval_loss": 2.2608485221862793,
+      "eval_runtime": 80.4976,
+      "eval_samples_per_second": 62.114,
+      "eval_steps_per_second": 15.528,
+      "num_input_tokens_seen": 85971046944,
+      "step": 152000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 84922496000,
+  "num_input_tokens_seen": 85971046944,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -26905,7 +27083,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.502973280567296e+20,
+  "total_flos": 1.5215307197191743e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null