Training in progress, step 39000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:240c5cdec4cb01ee28e7889eac5b35ac43b958d113ffd87aca906fc3f6ba3999
+oid sha256:2777be8c9cebd463e196323b155cb984733b00d18983e4b17294e9cb27c96958
 size 301235464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:899944e3f30352152c2648291ab1bb55289c83f5ec2e3de0e67c017363d88400
+oid sha256:10952b1300470216e5272efd12e330a8fee0d40316cade0bcf063631970529e4
 size 602335994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f48318ea481718bb688727479092abd5873b069ef497afe0690317d3f1864c6
+oid sha256:1a19c89868332b867e56c9f2182201b39f415614a12bb32a1b1436d1eb0c0433
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b9f11080dc8caed5e3c50cfbb46586ae36896ccfee6afab64bede4080bf44b1
+oid sha256:0453f791eed05815dae518781dc172eec5529318c2577a889d73a15d6a871e53
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1812609561515437,
+  "epoch": 0.18603098131342644,
   "eval_steps": 500,
-  "global_step": 38000,
+  "global_step": 39000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6772,11 +6772,189 @@
       "eval_steps_per_second": 24.217,
       "num_input_tokens_seen": 9961467456,
       "step": 38000
+    },
+    {
+      "epoch": 0.18149945740963783,
+      "grad_norm": 0.19376301765441895,
+      "learning_rate": 0.001,
+      "loss": 2.6274,
+      "num_input_tokens_seen": 9974574656,
+      "step": 38050
+    },
+    {
+      "epoch": 0.18173795866773199,
+      "grad_norm": 0.2077150195837021,
+      "learning_rate": 0.001,
+      "loss": 2.6303,
+      "num_input_tokens_seen": 9987681856,
+      "step": 38100
+    },
+    {
+      "epoch": 0.18197645992582612,
+      "grad_norm": 0.19407787919044495,
+      "learning_rate": 0.001,
+      "loss": 2.6246,
+      "num_input_tokens_seen": 10000789056,
+      "step": 38150
+    },
+    {
+      "epoch": 0.18221496118392025,
+      "grad_norm": 0.20558005571365356,
+      "learning_rate": 0.001,
+      "loss": 2.6291,
+      "num_input_tokens_seen": 10013896256,
+      "step": 38200
+    },
+    {
+      "epoch": 0.18245346244201438,
+      "grad_norm": 0.22928735613822937,
+      "learning_rate": 0.001,
+      "loss": 2.6336,
+      "num_input_tokens_seen": 10027003456,
+      "step": 38250
+    },
+    {
+      "epoch": 0.1826919637001085,
+      "grad_norm": 0.23481298983097076,
+      "learning_rate": 0.001,
+      "loss": 2.6412,
+      "num_input_tokens_seen": 10040110656,
+      "step": 38300
+    },
+    {
+      "epoch": 0.18293046495820264,
+      "grad_norm": 0.19808940589427948,
+      "learning_rate": 0.001,
+      "loss": 2.6395,
+      "num_input_tokens_seen": 10053217856,
+      "step": 38350
+    },
+    {
+      "epoch": 0.1831689662162968,
+      "grad_norm": 0.20152992010116577,
+      "learning_rate": 0.001,
+      "loss": 2.6224,
+      "num_input_tokens_seen": 10066325056,
+      "step": 38400
+    },
+    {
+      "epoch": 0.18340746747439093,
+      "grad_norm": 0.18065959215164185,
+      "learning_rate": 0.001,
+      "loss": 2.626,
+      "num_input_tokens_seen": 10079432256,
+      "step": 38450
+    },
+    {
+      "epoch": 0.18364596873248507,
+      "grad_norm": 0.20382963120937347,
+      "learning_rate": 0.001,
+      "loss": 2.6382,
+      "num_input_tokens_seen": 10092539456,
+      "step": 38500
+    },
+    {
+      "epoch": 0.18364596873248507,
+      "eval_loss": 2.5152854919433594,
+      "eval_runtime": 51.2566,
+      "eval_samples_per_second": 97.548,
+      "eval_steps_per_second": 24.387,
+      "num_input_tokens_seen": 10092539456,
+      "step": 38500
+    },
+    {
+      "epoch": 0.1838844699905792,
+      "grad_norm": 0.17728358507156372,
+      "learning_rate": 0.001,
+      "loss": 2.6293,
+      "num_input_tokens_seen": 10105646656,
+      "step": 38550
+    },
+    {
+      "epoch": 0.18412297124867333,
+      "grad_norm": 0.20164869725704193,
+      "learning_rate": 0.001,
+      "loss": 2.6372,
+      "num_input_tokens_seen": 10118753856,
+      "step": 38600
+    },
+    {
+      "epoch": 0.18436147250676746,
+      "grad_norm": 0.20125731825828552,
+      "learning_rate": 0.001,
+      "loss": 2.6326,
+      "num_input_tokens_seen": 10131861056,
+      "step": 38650
+    },
+    {
+      "epoch": 0.18459997376486162,
+      "grad_norm": 0.21193954348564148,
+      "learning_rate": 0.001,
+      "loss": 2.6249,
+      "num_input_tokens_seen": 10144968256,
+      "step": 38700
+    },
+    {
+      "epoch": 0.18483847502295575,
+      "grad_norm": 0.1925983726978302,
+      "learning_rate": 0.001,
+      "loss": 2.6424,
+      "num_input_tokens_seen": 10158075456,
+      "step": 38750
+    },
+    {
+      "epoch": 0.18507697628104988,
+      "grad_norm": 0.19814860820770264,
+      "learning_rate": 0.001,
+      "loss": 2.6431,
+      "num_input_tokens_seen": 10171182656,
+      "step": 38800
+    },
+    {
+      "epoch": 0.185315477539144,
+      "grad_norm": 0.1909031718969345,
+      "learning_rate": 0.001,
+      "loss": 2.6068,
+      "num_input_tokens_seen": 10184289856,
+      "step": 38850
+    },
+    {
+      "epoch": 0.18555397879723814,
+      "grad_norm": 0.20779775083065033,
+      "learning_rate": 0.001,
+      "loss": 2.625,
+      "num_input_tokens_seen": 10197397056,
+      "step": 38900
+    },
+    {
+      "epoch": 0.1857924800553323,
+      "grad_norm": 0.1768522411584854,
+      "learning_rate": 0.001,
+      "loss": 2.6112,
+      "num_input_tokens_seen": 10210504256,
+      "step": 38950
+    },
+    {
+      "epoch": 0.18603098131342644,
+      "grad_norm": 0.20275786519050598,
+      "learning_rate": 0.001,
+      "loss": 2.6284,
+      "num_input_tokens_seen": 10223611456,
+      "step": 39000
+    },
+    {
+      "epoch": 0.18603098131342644,
+      "eval_loss": 2.5149083137512207,
+      "eval_runtime": 51.6703,
+      "eval_samples_per_second": 96.767,
+      "eval_steps_per_second": 24.192,
+      "num_input_tokens_seen": 10223611456,
+      "step": 39000
     }
   ],
   "logging_steps": 50,
   "max_steps": 70000,
-  "num_input_tokens_seen": 9961467456,
+  "num_input_tokens_seen": 10223611456,
   "num_train_epochs": 1,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -6791,7 +6969,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6647897684023706e+18,
+  "total_flos": 2.7349158469278106e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null