Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:babc82995071bc41aade3454d15ec9bb729d608997415d35bcd2c165bc782f33
+oid sha256:b4f41337c16bbe084c798d91fe80884b941ad473c29c7a3c2e78387c1c925122
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c51a1e2578eaad67acf69af76baea1d98fcce883b9129ee2d3fbcd75663d482
+oid sha256:9f5452cef5d7e0093291198e7194f831fb37ba1f0c57806e5b5f83f0e52897da
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ffba558654506832b5597bf972aa095b36602aaa1cc09e0d0d147c3a782cc8c
+oid sha256:4f3b0545016cdad2d62cf5db499381ad30693ddaf4d345902ba2e164e1c35fa8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79307bdfd3764f9f34027dd539012be032a8f7b79e1df2fd5965658a362e8053
+oid sha256:417c1988987eddde4f77d3ffdba42c9a2ff0d26748cbdfe17718489519eaea46
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52e3013cf1b9904d72d3b0a6acc6c9fb854b016b052426d7fd2097ca2a412319
+oid sha256:cee12974f8c2d6ce98f447f28f9516064d965f704fb182b349bb14faf4e1a345
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b9829c96e37ea15bd3e98d1f613a9ab5cc5cdeb64c689d1051eca410e52456
+oid sha256:902c8c64bdc3048a1f987011cd129962441dc8213f3b0350c8f2231e0dbf883e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
+oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.856473922729492,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.3093289689034369,
+  "best_metric": 3.767355442047119,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 1.9639934533551555,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 178.389,
       "eval_steps_per_second": 46.381,
       "step": 50
+    },
+    {
+      "epoch": 1.3355155482815058,
+      "grad_norm": 0.37725579738616943,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 3.7317,
+      "step": 51
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 0.4553833603858948,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 3.7528,
+      "step": 52
+    },
+    {
+      "epoch": 1.3878887070376433,
+      "grad_norm": 0.4247891306877136,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 3.8082,
+      "step": 53
+    },
+    {
+      "epoch": 1.414075286415712,
+      "grad_norm": 0.45754310488700867,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 3.8597,
+      "step": 54
+    },
+    {
+      "epoch": 1.4402618657937807,
+      "grad_norm": 0.40189892053604126,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 3.8544,
+      "step": 55
+    },
+    {
+      "epoch": 1.4664484451718494,
+      "grad_norm": 0.4472440779209137,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 3.902,
+      "step": 56
+    },
+    {
+      "epoch": 1.492635024549918,
+      "grad_norm": 0.7986133694648743,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 4.3171,
+      "step": 57
+    },
+    {
+      "epoch": 1.518821603927987,
+      "grad_norm": 0.47378429770469666,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 3.2801,
+      "step": 58
+    },
+    {
+      "epoch": 1.5450081833060556,
+      "grad_norm": 0.609893798828125,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 3.5901,
+      "step": 59
+    },
+    {
+      "epoch": 1.5711947626841245,
+      "grad_norm": 0.5858629941940308,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 3.601,
+      "step": 60
+    },
+    {
+      "epoch": 1.5973813420621932,
+      "grad_norm": 0.37681153416633606,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 3.7124,
+      "step": 61
+    },
+    {
+      "epoch": 1.6235679214402619,
+      "grad_norm": 0.338227778673172,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 3.7552,
+      "step": 62
+    },
+    {
+      "epoch": 1.6497545008183305,
+      "grad_norm": 0.35423874855041504,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 3.7876,
+      "step": 63
+    },
+    {
+      "epoch": 1.6759410801963992,
+      "grad_norm": 0.4390277862548828,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 3.8012,
+      "step": 64
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 0.563541829586029,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 3.8544,
+      "step": 65
+    },
+    {
+      "epoch": 1.7283142389525368,
+      "grad_norm": 0.7141799330711365,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 4.0238,
+      "step": 66
+    },
+    {
+      "epoch": 1.7545008183306057,
+      "grad_norm": 0.4013899862766266,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 3.1346,
+      "step": 67
+    },
+    {
+      "epoch": 1.7806873977086743,
+      "grad_norm": 0.3977162539958954,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 3.8809,
+      "step": 68
+    },
+    {
+      "epoch": 1.806873977086743,
+      "grad_norm": 0.35375577211380005,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 3.6103,
+      "step": 69
+    },
+    {
+      "epoch": 1.8330605564648117,
+      "grad_norm": 0.3449622094631195,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 3.6076,
+      "step": 70
+    },
+    {
+      "epoch": 1.8592471358428804,
+      "grad_norm": 0.3213866651058197,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 3.712,
+      "step": 71
+    },
+    {
+      "epoch": 1.8854337152209493,
+      "grad_norm": 0.34646686911582947,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.7291,
+      "step": 72
+    },
+    {
+      "epoch": 1.9116202945990182,
+      "grad_norm": 0.3628241717815399,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 3.8293,
+      "step": 73
+    },
+    {
+      "epoch": 1.9378068739770868,
+      "grad_norm": 0.37866660952568054,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 3.8291,
+      "step": 74
+    },
+    {
+      "epoch": 1.9639934533551555,
+      "grad_norm": 0.4907776415348053,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 3.8753,
+      "step": 75
+    },
+    {
+      "epoch": 1.9639934533551555,
+      "eval_loss": 3.767355442047119,
+      "eval_runtime": 0.2893,
+      "eval_samples_per_second": 172.844,
+      "eval_steps_per_second": 44.939,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.13737243557888e+16,
+  "total_flos": 1.70605865336832e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null