Training in progress, step 150000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b87dded127d40fd82c03235b1698dfe33a8b5f87187ba074bf40022236624c6
+oid sha256:374909593e8ea311703df093fe62f4e04001dd17e3c49fbf489dab7fba5c0d5e
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c47d38cecaa63e531df29e38e9afb0727c11e9a4b57b059ee2acbb0fb1f4d3
+oid sha256:8b12ee754bf5fd72453fbeae9c7e6862a347afe5a2e5e26d7a0545500ccc9bf8
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b3f339c8acfe7277fe2df77c27fc1a5816faed78935e9068ab888b7bb106bcc
+oid sha256:75979b1827f6aedbded5556bf5c04453d08a32a155f909439c67d10d01c05c41
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c40e8b457d57718c67b26e249dafca477bb77feb974e04c20b75eee25d0b14aa
+oid sha256:305ea49d7e626826ceaad34f0959f2e71b7074c795df15fc38b6daeaea82d52e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.272994172816591,
+  "epoch": 3.2949602311378485,
   "eval_steps": 500,
-  "global_step": 149000,
+  "global_step": 150000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -26530,11 +26530,189 @@
       "eval_steps_per_second": 15.448,
       "num_input_tokens_seen": 82825402528,
       "step": 149000
+    },
+    {
+      "epoch": 3.2740924757326537,
+      "grad_norm": 0.09636425226926804,
+      "learning_rate": 0.0001,
+      "loss": 2.3512,
+      "num_input_tokens_seen": 82877831328,
+      "step": 149050
+    },
+    {
+      "epoch": 3.275190778648717,
+      "grad_norm": 0.09321967512369156,
+      "learning_rate": 0.0001,
+      "loss": 2.3464,
+      "num_input_tokens_seen": 82930260128,
+      "step": 149100
+    },
+    {
+      "epoch": 3.2762890815647796,
+      "grad_norm": 0.09646619111299515,
+      "learning_rate": 0.0001,
+      "loss": 2.3477,
+      "num_input_tokens_seen": 82982684224,
+      "step": 149150
+    },
+    {
+      "epoch": 3.2773873844808423,
+      "grad_norm": 0.09394371509552002,
+      "learning_rate": 0.0001,
+      "loss": 2.3436,
+      "num_input_tokens_seen": 83035113024,
+      "step": 149200
+    },
+    {
+      "epoch": 3.2784856873969055,
+      "grad_norm": 0.09308401495218277,
+      "learning_rate": 0.0001,
+      "loss": 2.3543,
+      "num_input_tokens_seen": 83087541664,
+      "step": 149250
+    },
+    {
+      "epoch": 3.279583990312968,
+      "grad_norm": 0.09759179502725601,
+      "learning_rate": 0.0001,
+      "loss": 2.3418,
+      "num_input_tokens_seen": 83139969344,
+      "step": 149300
+    },
+    {
+      "epoch": 3.280682293229031,
+      "grad_norm": 0.0901869386434555,
+      "learning_rate": 0.0001,
+      "loss": 2.3484,
+      "num_input_tokens_seen": 83192395872,
+      "step": 149350
+    },
+    {
+      "epoch": 3.281780596145094,
+      "grad_norm": 0.0878322646021843,
+      "learning_rate": 0.0001,
+      "loss": 2.3497,
+      "num_input_tokens_seen": 83244824672,
+      "step": 149400
+    },
+    {
+      "epoch": 3.282878899061157,
+      "grad_norm": 0.09223738312721252,
+      "learning_rate": 0.0001,
+      "loss": 2.3505,
+      "num_input_tokens_seen": 83297245472,
+      "step": 149450
+    },
+    {
+      "epoch": 3.28397720197722,
+      "grad_norm": 0.0960436537861824,
+      "learning_rate": 0.0001,
+      "loss": 2.348,
+      "num_input_tokens_seen": 83349674016,
+      "step": 149500
+    },
+    {
+      "epoch": 3.28397720197722,
+      "eval_loss": 2.2621405124664307,
+      "eval_runtime": 80.8246,
+      "eval_samples_per_second": 61.862,
+      "eval_steps_per_second": 15.466,
+      "num_input_tokens_seen": 83349674016,
+      "step": 149500
+    },
+    {
+      "epoch": 3.2850755048932827,
+      "grad_norm": 0.09093570709228516,
+      "learning_rate": 0.0001,
+      "loss": 2.3531,
+      "num_input_tokens_seen": 83402102304,
+      "step": 149550
+    },
+    {
+      "epoch": 3.2861738078093454,
+      "grad_norm": 0.09345680475234985,
+      "learning_rate": 0.0001,
+      "loss": 2.3425,
+      "num_input_tokens_seen": 83454531104,
+      "step": 149600
+    },
+    {
+      "epoch": 3.2872721107254086,
+      "grad_norm": 0.09687989205121994,
+      "learning_rate": 0.0001,
+      "loss": 2.3467,
+      "num_input_tokens_seen": 83506956512,
+      "step": 149650
+    },
+    {
+      "epoch": 3.2883704136414713,
+      "grad_norm": 0.09994108229875565,
+      "learning_rate": 0.0001,
+      "loss": 2.3526,
+      "num_input_tokens_seen": 83559385312,
+      "step": 149700
+    },
+    {
+      "epoch": 3.2894687165575345,
+      "grad_norm": 0.0894683226943016,
+      "learning_rate": 0.0001,
+      "loss": 2.3545,
+      "num_input_tokens_seen": 83611807424,
+      "step": 149750
+    },
+    {
+      "epoch": 3.290567019473597,
+      "grad_norm": 0.08919432759284973,
+      "learning_rate": 0.0001,
+      "loss": 2.3375,
+      "num_input_tokens_seen": 83664236224,
+      "step": 149800
+    },
+    {
+      "epoch": 3.29166532238966,
+      "grad_norm": 0.0880848690867424,
+      "learning_rate": 0.0001,
+      "loss": 2.3411,
+      "num_input_tokens_seen": 83716662592,
+      "step": 149850
+    },
+    {
+      "epoch": 3.292763625305723,
+      "grad_norm": 0.09474777430295944,
+      "learning_rate": 0.0001,
+      "loss": 2.3454,
+      "num_input_tokens_seen": 83769091072,
+      "step": 149900
+    },
+    {
+      "epoch": 3.293861928221786,
+      "grad_norm": 0.09384060651063919,
+      "learning_rate": 0.0001,
+      "loss": 2.3532,
+      "num_input_tokens_seen": 83821518880,
+      "step": 149950
+    },
+    {
+      "epoch": 3.2949602311378485,
+      "grad_norm": 0.09099478274583817,
+      "learning_rate": 0.0001,
+      "loss": 2.345,
+      "num_input_tokens_seen": 83873945408,
+      "step": 150000
+    },
+    {
+      "epoch": 3.2949602311378485,
+      "eval_loss": 2.2621686458587646,
+      "eval_runtime": 80.2172,
+      "eval_samples_per_second": 62.331,
+      "eval_steps_per_second": 15.583,
+      "num_input_tokens_seen": 83873945408,
+      "step": 150000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 82825402528,
+  "num_input_tokens_seen": 83873945408,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -26549,7 +26727,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.465858551211389e+20,
+  "total_flos": 1.484415847645176e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null