MHGanainy/mgpt-lora-multi-belgium-imbalanced-1024

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # mgpt-lora-multi-belgium-imbalanced-1024
 
 This model is a fine-tuned version of [ai-forever/mGPT](https://huggingface.co/ai-forever/mGPT) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6679
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.6678621768951416,
+    "eval_runtime": 44.6818,
+    "eval_samples_per_second": 78.981,
+    "eval_steps_per_second": 9.892,
+    "perplexity": 5.300823452549077,
+    "total_flos": 2.016828552422359e+17,
+    "train_loss": 3.3373708904914134,
+    "train_runtime": 461.7028,
+    "train_samples_per_second": 29.374,
+    "train_steps_per_second": 3.673
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.6678621768951416,
+    "eval_runtime": 44.6818,
+    "eval_samples_per_second": 78.981,
+    "eval_steps_per_second": 9.892,
+    "perplexity": 5.300823452549077
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.016828552422359e+17,
+    "train_loss": 3.3373708904914134,
+    "train_runtime": 461.7028,
+    "train_samples_per_second": 29.374,
+    "train_steps_per_second": 3.673
+}

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1696,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0589622641509434,
+      "grad_norm": 2.7711544036865234,
+      "learning_rate": 1.4749262536873157e-06,
+      "loss": 5.9761,
+      "step": 100
+    },
+    {
+      "epoch": 0.1179245283018868,
+      "grad_norm": 4.138933181762695,
+      "learning_rate": 2.9498525073746313e-06,
+      "loss": 5.903,
+      "step": 200
+    },
+    {
+      "epoch": 0.17688679245283018,
+      "grad_norm": 4.181414604187012,
+      "learning_rate": 4.424778761061948e-06,
+      "loss": 5.4059,
+      "step": 300
+    },
+    {
+      "epoch": 0.2358490566037736,
+      "grad_norm": 2.9454779624938965,
+      "learning_rate": 5.899705014749263e-06,
+      "loss": 4.4503,
+      "step": 400
+    },
+    {
+      "epoch": 0.294811320754717,
+      "grad_norm": 1.2399593591690063,
+      "learning_rate": 7.374631268436579e-06,
+      "loss": 3.7966,
+      "step": 500
+    },
+    {
+      "epoch": 0.35377358490566035,
+      "grad_norm": 2.2943074703216553,
+      "learning_rate": 8.849557522123895e-06,
+      "loss": 3.4932,
+      "step": 600
+    },
+    {
+      "epoch": 0.41273584905660377,
+      "grad_norm": 15.703469276428223,
+      "learning_rate": 1.032448377581121e-05,
+      "loss": 3.3726,
+      "step": 700
+    },
+    {
+      "epoch": 0.4716981132075472,
+      "grad_norm": 1.7949004173278809,
+      "learning_rate": 1.1799410029498525e-05,
+      "loss": 3.2697,
+      "step": 800
+    },
+    {
+      "epoch": 0.5306603773584906,
+      "grad_norm": 1.830142855644226,
+      "learning_rate": 1.3274336283185843e-05,
+      "loss": 3.1635,
+      "step": 900
+    },
+    {
+      "epoch": 0.589622641509434,
+      "grad_norm": 2.7658205032348633,
+      "learning_rate": 1.4749262536873157e-05,
+      "loss": 2.9904,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6485849056603774,
+      "grad_norm": 3.1004638671875,
+      "learning_rate": 1.6224188790560475e-05,
+      "loss": 2.7409,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7075471698113207,
+      "grad_norm": 2.6082653999328613,
+      "learning_rate": 1.769911504424779e-05,
+      "loss": 2.4229,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7665094339622641,
+      "grad_norm": 1.7147059440612793,
+      "learning_rate": 1.9174041297935103e-05,
+      "loss": 2.1415,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8254716981132075,
+      "grad_norm": 2.224583625793457,
+      "learning_rate": 1.9184869857459233e-05,
+      "loss": 1.9829,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8844339622641509,
+      "grad_norm": 2.0863797664642334,
+      "learning_rate": 1.2379351950426188e-05,
+      "loss": 1.9055,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 2.082080125808716,
+      "learning_rate": 3.6828899374674933e-06,
+      "loss": 1.8385,
+      "step": 1600
+    },
+    {
+      "epoch": 1.0,
+      "step": 1696,
+      "total_flos": 2.016828552422359e+17,
+      "train_loss": 3.3373708904914134,
+      "train_runtime": 461.7028,
+      "train_samples_per_second": 29.374,
+      "train_steps_per_second": 3.673
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1696,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.016828552422359e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}