Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cbce5af76e1e48d89a397d83170bc57c3eb9658c035203bed506dd64251a17a
+oid sha256:9580f23f6650701b8c5c6baa7b6251793876fc45c8700caf4e48d91b6ad89806
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:138b30553fd9154412683c6e5b96709767ee98389d8f5203e88b0fa44dfbe649
+oid sha256:f5a855a05342866a4aba16944f07a8978153f6a90eff7647124c560db0db5cc6
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a25e101f39164e92467712a28e8e6cb74e5f3b47c630735ff43fc58e6de6580
+oid sha256:c899beef0e4b648cad8954a66a8d655d219bebd0e6f90f7ad69eea43e18a96c4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b80d146b8b37f82a1962ba385b8329fd6c2c35ba5116c53e131bb661ab681b
+oid sha256:ed29baad6d6611c736eccf18bdd7afdc5d6f3612cde61e7bfa83472d3e2068d2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.11406784504652023,
-  "best_model_checkpoint": "miner_id_besimray/checkpoint-60",
-  "epoch": 0.7717041800643086,
+  "best_metric": 0.10349678248167038,
+  "best_model_checkpoint": "miner_id_besimray/checkpoint-80",
+  "epoch": 1.0289389067524115,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -459,6 +459,154 @@
       "eval_samples_per_second": 23.441,
       "eval_steps_per_second": 2.43,
       "step": 60
+    },
+    {
+      "epoch": 0.7845659163987139,
+      "grad_norm": 1.2640259265899658,
+      "learning_rate": 0.00014135585049665207,
+      "loss": 0.1332,
+      "step": 61
+    },
+    {
+      "epoch": 0.797427652733119,
+      "grad_norm": 2.274766445159912,
+      "learning_rate": 0.00013930250316539238,
+      "loss": 0.1278,
+      "step": 62
+    },
+    {
+      "epoch": 0.8102893890675241,
+      "grad_norm": 2.1382172107696533,
+      "learning_rate": 0.00013722936584019453,
+      "loss": 0.1881,
+      "step": 63
+    },
+    {
+      "epoch": 0.8231511254019293,
+      "grad_norm": 1.8246463537216187,
+      "learning_rate": 0.0001351374824081343,
+      "loss": 0.1527,
+      "step": 64
+    },
+    {
+      "epoch": 0.8360128617363344,
+      "grad_norm": 2.0515213012695312,
+      "learning_rate": 0.00013302790619551674,
+      "loss": 0.178,
+      "step": 65
+    },
+    {
+      "epoch": 0.8488745980707395,
+      "grad_norm": 1.2779912948608398,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.1207,
+      "step": 66
+    },
+    {
+      "epoch": 0.8617363344051447,
+      "grad_norm": 1.3247287273406982,
+      "learning_rate": 0.00012875993274320173,
+      "loss": 0.1003,
+      "step": 67
+    },
+    {
+      "epoch": 0.8745980707395499,
+      "grad_norm": 1.5200964212417603,
+      "learning_rate": 0.00012660368455666752,
+      "loss": 0.1518,
+      "step": 68
+    },
+    {
+      "epoch": 0.887459807073955,
+      "grad_norm": 1.2721142768859863,
+      "learning_rate": 0.0001244340406137894,
+      "loss": 0.153,
+      "step": 69
+    },
+    {
+      "epoch": 0.9003215434083601,
+      "grad_norm": 1.0692765712738037,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.1125,
+      "step": 70
+    },
+    {
+      "epoch": 0.9131832797427653,
+      "grad_norm": 0.9016242027282715,
+      "learning_rate": 0.00012005894157832729,
+      "loss": 0.0923,
+      "step": 71
+    },
+    {
+      "epoch": 0.9260450160771704,
+      "grad_norm": 0.9723653197288513,
+      "learning_rate": 0.00011785568947986367,
+      "loss": 0.0711,
+      "step": 72
+    },
+    {
+      "epoch": 0.9389067524115756,
+      "grad_norm": 1.1226719617843628,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.0733,
+      "step": 73
+    },
+    {
+      "epoch": 0.9517684887459807,
+      "grad_norm": 0.7384305596351624,
+      "learning_rate": 0.00011342332658176555,
+      "loss": 0.0509,
+      "step": 74
+    },
+    {
+      "epoch": 0.9646302250803859,
+      "grad_norm": 1.1397889852523804,
+      "learning_rate": 0.00011119644761033078,
+      "loss": 0.1132,
+      "step": 75
+    },
+    {
+      "epoch": 0.977491961414791,
+      "grad_norm": 0.7340204119682312,
+      "learning_rate": 0.00010896393089034336,
+      "loss": 0.0548,
+      "step": 76
+    },
+    {
+      "epoch": 0.9903536977491961,
+      "grad_norm": 1.2681351900100708,
+      "learning_rate": 0.00010672690056120399,
+      "loss": 0.128,
+      "step": 77
+    },
+    {
+      "epoch": 1.0032154340836013,
+      "grad_norm": 1.2592830657958984,
+      "learning_rate": 0.00010448648303505151,
+      "loss": 0.1188,
+      "step": 78
+    },
+    {
+      "epoch": 1.0160771704180065,
+      "grad_norm": 0.7425731420516968,
+      "learning_rate": 0.00010224380642958052,
+      "loss": 0.0486,
+      "step": 79
+    },
+    {
+      "epoch": 1.0289389067524115,
+      "grad_norm": 1.5176936388015747,
+      "learning_rate": 0.0001,
+      "loss": 0.1457,
+      "step": 80
+    },
+    {
+      "epoch": 1.0289389067524115,
+      "eval_loss": 0.10349678248167038,
+      "eval_runtime": 6.832,
+      "eval_samples_per_second": 24.005,
+      "eval_steps_per_second": 2.488,
+      "step": 80
     }
   ],
   "logging_steps": 1,
@@ -487,7 +635,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.446291621543936e+16,
+  "total_flos": 1.911441083203584e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null